© 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. 12829
    Prev
    Next
    INDEX
    Explanations

    contact details and services

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

    STAR method, individual, candidates, increased

    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
    builtin
    0.50
    authorization
    0.46
    PlainText
    0.46
    क्का
    0.45
    မဟုတ်
    0.44
    financing
    0.44
     modernization
    0.44
    夏
    0.44
    Avro
    0.43
    supabase
    0.43
    POSITIVE LOGITS
     bedre
    0.49
    ☎
    0.45
     обраща
    0.44
     alguns
    0.43
     어려
    0.43
     ஏற்படும்
    0.42
    mares
    0.41
     Fehler
    0.41
    ৭
    0.41
     alloys
    0.41
    Activations Density 0.000%

    No Known Activations