© 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. 89900
    Prev
    Next
    INDEX
    Explanations

    updated daily

    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
    ႅ
    0.54
    OW
    0.52
    𝘐
    0.50
    años
    0.47
    goài
    0.46
    ўся
    0.46
    OnUiThread
    0.46
     ダ
    0.45
     thị
    0.44
    IGN
    0.43
    POSITIVE LOGITS
     spectrom
    0.52
     Faust
    0.50
     GAP
    0.48
     Namespace
    0.46
     home
    0.46
     Vé
    0.45
     Faun
    0.45
     Collo
    0.45
     extermin
    0.43
     classed
    0.43
    Activations Density 0.000%

    No Known Activations