© 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. 158353
    Prev
    Next
    INDEX
    Explanations

    drink

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

    characters and qualities

    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
    但在
    0.46
     ينا
    0.46
    傾向
    0.43
    ORK
    0.41
    GroupBy
    0.39
    <unused11>
    0.39
     tumor
    0.39
    Issue
    0.39
    BackgroundColor
    0.39
     tumorigen
    0.39
    POSITIVE LOGITS
    et
    0.56
    it
    0.46
    ’
    0.46
    ize
    0.45
    ur
    0.45
    and
    0.43
    ae
    0.43
    ços
    0.42
     Says
    0.42
     Federal
    0.42
    Activations Density 0.000%

    No Known Activations