© 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. 104107
    Prev
    Next
    INDEX
    Explanations

    own items or properties

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

    specifications or 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
    ﹁
    0.59
     വേദിക
    0.55
    mDatas
    0.55
    竰
    0.54
    <unused79>
    0.52
     ciência
    0.52
     piatto
    0.52
    চ্ছিলাম
    0.52
     전달
    0.51
     liberación
    0.51
    POSITIVE LOGITS
    In
    0.66
    1
    0.61
    ;
    0.60
    6
    0.59
    8
    0.55
    <b>
    0.55
    4
    0.55
    sp
    0.54
    0.54
    Q
    0.53
    Activations Density 0.000%

    No Known Activations