© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4845
    Prev
    Next
    INDEX
    Explanations

    word stems

    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
    ंना
    1.56
    )
    1.48
    ATED
    1.34
    tedir
    1.34
    LY
    1.33
     Tauri
    1.29
    ]}{\
    1.28
    ्स
    1.27
    ారు
    1.27
    xture
    1.26
    POSITIVE LOGITS
    it
    1.59
    ar
    1.58
    as
    1.55
    this
    1.43
    đ
    1.39
    on
    1.35
    at
    1.34
    el
    1.34
    int
    1.30
    w
    1.30
    Activations Density 0.166%

    No Known Activations