© 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. 59427
    Prev
    Next
    INDEX
    Explanations

    way someone

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

    not literally

    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
    u
    0.50
     Compensation
    0.47
    us
    0.46
    ar
    0.46
     Seal
    0.44
    ύ
    0.44
    ur
    0.44
    ιβ
    0.44
    in
    0.44
    啷
    0.43
    POSITIVE LOGITS
     صورت
    0.48
    GYPT
    0.47
    قتها
    0.46
     repressed
    0.46
    letos
    0.46
     antigos
    0.46
     verband
    0.45
     ಹೇಳ
    0.44
     coalgebras
    0.42
     deshalb
    0.42
    Activations Density 0.000%

    No Known Activations