© 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. 232834
    Prev
    Next
    INDEX
    Explanations

    team names after hyphen

    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
    .\
    0.30
    Referensi
    0.30
    前記
    0.30
    said
    0.29
     Corresponding
    0.29
     Saltar
    0.29
    pesar
    0.28
    и
    0.28
    .’”
    0.28
    estable
    0.28
    POSITIVE LOGITS
     urb
    0.29
    <unused294>
    0.29
     organiques
    0.29
     politiques
    0.28
     élément
    0.28
     dziś
    0.28
     telecoms
    0.28
     passent
    0.27
    <unused2186>
    0.27
     nowy
    0.27
    Activations Density 0.007%

    No Known Activations