© 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. 141593
    Prev
    Next
    INDEX
    Explanations

    wide screen

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

    list items preceded by specific tokens

    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
    嵐
    0.49
    Zap
    0.48
     yarı
    0.47
    нит
    0.46
     sostit
    0.43
    Justin
    0.43
    Jeremy
    0.43
    Diego
    0.43
    P
    0.42
     impianti
    0.42
    POSITIVE LOGITS
    averaged
    0.49
    translated
    0.46
    ies
    0.46
    চন্দ্রের
    0.45
    ovsk
    0.44
     Expenditures
    0.44
     Origins
    0.44
    renzia
    0.44
    ధం
    0.44
    shaus
    0.43
    Activations Density 0.001%

    No Known Activations