© 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. 208408
    Prev
    Next
    INDEX
    Explanations

    expiration, instead, unintentionally

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

    same as

    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
    وتي
    0.61
    ائق
    0.60
    صر
    0.53
    وار
    0.52
    બ
    0.52
    ال
    0.51
    وم
    0.51
    ظر
    0.50
    ند
    0.50
    战争
    0.49
    POSITIVE LOGITS
    dialect
    0.48
     शक्यता
    0.47
    receiving
    0.47
    conditioning
    0.46
     ENT
    0.46
    そらく
    0.45
    受賞
    0.45
    initWith
    0.45
     CPI
    0.44
    prüfung
    0.44
    Activations Density 0.000%

    No Known Activations