© 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. 60157
    Prev
    Next
    INDEX
    Explanations

    occur in, expensive car, were you

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

    delay, minutes, variation, dissolution

    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
     забруд
    0.54
     malattia
    0.47
     الك
    0.46
     півні
    0.46
     スタ
    0.46
     ヒ
    0.46
     숨
    0.45
     洗
    0.45
    Celltype
    0.45
     ベルト
    0.45
    POSITIVE LOGITS
    toLocale
    0.44
    .^
    0.43
     Maitland
    0.43
     Ideally
    0.43
     Tables
    0.42
    Ideally
    0.42
    amalla
    0.41
    傥
    0.41
    tabs
    0.41
     Ngọc
    0.40
    Activations Density 0.000%

    No Known Activations