© 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. 26517
    Prev
    Next
    INDEX
    Explanations

    class members accessed via dot

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

    programming constructs followed by dots

    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
    വ
    0.46
    Prosecutors
    0.43
    股东
    0.42
    pite
    0.42
    Being
    0.41
    ুলি
    0.41
    満足
    0.41
     metabolized
    0.41
    Chairman
    0.41
    煒
    0.41
    POSITIVE LOGITS
    .”.
    0.42
    .""
    0.41
    aanse
    0.41
    .".
    0.41
     наука
    0.40
    .,"
    0.39
     Describe
    0.39
     કારણ
    0.39
    “.
    0.38
    ändern
    0.38
    Activations Density 0.000%

    No Known Activations