© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159549
    Prev
    Next
    INDEX
    Explanations

    race and animals

    np_acts-logits-general · gemini-2.5-flash-lite

    delightfully quirky explains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TInner
    0.50
     বাঙ্গাল
    0.49
    ু
    0.49
    Escolh
    0.48
     писа
    0.47
     Kids
    0.46
     Masks
    0.46
     fiume
    0.46
     Kedua
    0.46
    룺
    0.45
    POSITIVE LOGITS
    t
    0.55
    of
    0.54
    websocket
    0.47
    sed
    0.44
    ↵↵
    0.44
    application
    0.43
    尼亚
    0.42
    .
    0.42
    se
    0.42
    in
    0.41
    Activations Density 0.000%

    No Known Activations