© 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. 102420
    Prev
    Next
    INDEX
    Explanations

    configuration files and code

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

    rule type pattern

    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
     needless
    0.46
     fier
    0.45
     outcast
    0.44
     Rien
    0.44
     Quand
    0.42
    <h3>
    0.42
     Constru
    0.42
     heure
    0.41
     merciless
    0.41
     Needless
    0.40
    POSITIVE LOGITS
    [,,"
    0.41
     తిన
    0.40
    审批
    0.39
     providers
    0.39
    ㈣
    0.39
     খাবার
    0.38
    িবে
    0.38
    providers
    0.38
     caramelized
    0.37
    <unused1874>
    0.37
    Activations Density 0.010%

    No Known Activations