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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8675
    Prev
    Next
    INDEX
    Explanations

    from [X]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    у
    2.93
    е
    2.85
    一个
    2.53
    geht
    2.49
    নের
    2.47
    ுக்
    2.46
    footed
    2.39
    νες
    2.38
    Json
    2.34
    내가
    2.31
    POSITIVE LOGITS
     whence
    4.15
    ባድ
    4.06
     afar
    4.06
     segi
    4.01
    ፍተኛ
    3.75
    r
    3.40
     thence
    3.28
     비롯
    3.06
    t
    3.03
     طریق
    3.00
    Activations Density 0.222%

    No Known Activations