© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 5904
    Prev
    Next
    INDEX
    Explanations

    **TOP_ACTIVATING_TEXTS**:* `Who is thai prime minister` -> Model: `The current Prime Minister of Thailand is **Srettha Thavisin**. He`* `Who is the current monarch of the United Kingdom?` -> Model: `The current monarch of the United Kingdom is **King Charles`* `who is beshine` -> Model: `Beshine (real name likely **Beshine O'Brien**) is`* `who is cosmicqbit on internet` -> Model: `CosmicQbit is a popular streamer and content creator primarily known for`**Analysis**:* All `TOP_ACTIVATING_TEXTS` are questions starting with "Who is...".* The `MAX_ACTIVATING_TOKENS` consistently show `is`.who is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     우
    1.69
    ra
    1.55
     의
    1.52
    나
    1.52
    새
    1.46
    rs
    1.45
    თ
    1.45
    gi
    1.45
     관련
    1.45
    jenja
    1.43
    POSITIVE LOGITS
     glycoproteins
    1.47
     primates
    1.41
    祀
    1.34
     alliances
    1.31
    ки
    1.30
    दारी
    1.30
     libres
    1.30
    ຜູ້
    1.30
    ೋ
    1.28
     cutaneous
    1.27
    Activations Density 0.239%

    No Known Activations