© 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. 242992
    Prev
    Next
    INDEX
    Explanations

    Apk file, record growth, lost information

    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
    Scaler
    0.52
    ;
    0.47
    Mosaic
    0.46
    ไง
    0.46
    ::<
    0.44
    ;_
    0.44
    ⚽
    0.43
    Production
    0.42
    Ll
    0.42
     vintage
    0.41
    POSITIVE LOGITS
     ஏராளமான
    0.55
     wymag
    0.55
     Sudah
    0.54
     실
    0.53
     важли
    0.53
     fertig
    0.53
     закін
    0.53
    agés
    0.51
    onik
    0.51
    ında
    0.51
    Activations Density 0.000%

    No Known Activations