© 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. 120374
    Prev
    Next
    INDEX
    Explanations

    risks and uncertainties

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

    `*args`, `**kwargs` in function definitions

    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
    tien
    0.56
     présente
    0.55
    слова
    0.52
    dataset
    0.52
     ټول
    0.51
     ဗ
    0.51
     موږ
    0.50
    <td>
    0.50
    toc
    0.50
    today
    0.50
    POSITIVE LOGITS
    ح
    0.54
    ryst
    0.52
     )
    0.50
    Options
    0.49
    াত
    0.47
     så
    0.46
    A
    0.46
    lal
    0.45
    Option
    0.44
    **)
    0.44
    Activations Density 0.000%

    No Known Activations