© 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. 79708
    Prev
    Next
    INDEX
    Explanations

    upcoming lineup, latest revisions, difference between

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

    phrased questions and statements

    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
     عليها
    0.49
    0.48
     বিনিম
    0.46
    紮
    0.46
     Konrad
    0.46
    上也
    0.45
     ग्
    0.45
    Kon
    0.43
     GLS
    0.43
     سند
    0.43
    POSITIVE LOGITS
    in
    0.52
    ammation
    0.52
    pek
    0.48
    ົມ
    0.47
    FORMANCE
    0.46
    itioners
    0.46
     biliary
    0.45
    フォーマンス
    0.45
    દ
    0.45
    igde
    0.44
    Activations Density 0.000%

    No Known Activations