© 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. 247174
    Prev
    Next
    INDEX
    Explanations

    physical records

    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
    :
    0.55
    Сере
    0.50
     quét
    0.46
    ’
    0.45
    Ска
    0.45
     영어
    0.44
     thử
    0.44
    :^(
    0.44
    .*/
    0.44
     języ
    0.44
    POSITIVE LOGITS
    لات
    0.46
     महाग
    0.46
    ات
    0.45
    ن
    0.45
    數字
    0.45
     spaceleft
    0.45
    不断的
    0.44
    იან
    0.44
    تالي
    0.44
    يير
    0.44
    Activations Density 0.000%

    No Known Activations