© 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. 61241
    Prev
    Next
    INDEX
    Explanations

    it truly

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

    Combined or changing states

    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
    ОР
    0.45
    К
    0.44
     zove
    0.44
    Ŋ
    0.43
    INIT
    0.43
    Somebody
    0.42
    凱
    0.42
     تعال
    0.41
    Boulder
    0.41
    靭
    0.41
    POSITIVE LOGITS
    elen
    0.43
    %]
    0.42
     Association
    0.41
     Andree
    0.41
    -]+
    0.41
     actual
    0.40
    damian
    0.40
     Montgomery
    0.40
     tình
    0.40
     Fitzsimmons
    0.40
    Activations Density 0.000%

    No Known Activations