© 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. 206374
    Prev
    Next
    INDEX
    Explanations

    this project

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

    check-ins and operational 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
    mique
    0.49
    лық
    0.45
    arlık
    0.45
    雩
    0.45
    agun
    0.44
    gyi
    0.43
     관계로
    0.43
    シティ
    0.43
    ваясь
    0.42
    的他
    0.42
    POSITIVE LOGITS
     accounting
    0.50
     redundant
    0.45
    FW
    0.44
     (“
    0.44
     Accounting
    0.44
    CEST
    0.44
    ي
    0.44
     glycoprotein
    0.42
    i
    0.42
     orth
    0.42
    Activations Density 0.000%

    No Known Activations