© 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. 160113
    Prev
    Next
    INDEX
    Explanations

    record date for stockholders

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

    company, research, cause, ensure

    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
    8
    0.52
    7
    0.50
    ジ
    0.49
    ouwen
    0.48
    /
    0.47
    6
    0.46
    4
    0.46
    5
    0.45
    ufthansa
    0.42
    付き
    0.42
    POSITIVE LOGITS
    ಹಾರ
    0.45
    чко
    0.44
    હાર
    0.43
    গর্
    0.43
    कूल
    0.42
    renamiento
    0.42
     problemler
    0.42
    UnaryOperation
    0.42
    有害
    0.41
    าล
    0.41
    Activations Density 0.000%

    No Known Activations