© 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. 115087
    Prev
    Next
    INDEX
    Explanations

    conference call

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

    to 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
    ски
    0.52
    ル
    0.52
    ளுக்கு
    0.52
    해주세요
    0.50
    лото
    0.50
     остается
    0.49
    сно
    0.45
    ?
    0.45
    的
    0.45
    лаш
    0.45
    POSITIVE LOGITS
    isfile
    0.45
     işte
    0.43
    ICES
    0.42
     kand
    0.42
    Executed
    0.42
     états
    0.41
    评标
    0.41
     ছায়
    0.41
     vuoden
    0.41
    لان
    0.40
    Activations Density 0.000%

    No Known Activations