© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    HTML `br` and new content

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

    code parsing

    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
    ون
    0.63
    م
    0.63
    ز
    0.57
    ду
    0.56
    ود
    0.54
    ୈ
    0.52
    CH
    0.50
    COOL
    0.50
    دت
    0.49
    人類
    0.49
    POSITIVE LOGITS
     были
    0.62
    _
    0.60
     σε
    0.59
     от
    0.58
     для
    0.57
     היה
    0.57
     запрос
    0.57
     Ще
    0.56
     был
    0.55
     використовувати
    0.54
    Activations Density 0.000%

    No Known Activations