© 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. 96997
    Prev
    Next
    INDEX
    Explanations

    provide additional

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

    identifies, new, essential

    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
    -
    0.57
     ard
    0.50
     (
    0.44
     pl
    0.42
     Mathis
    0.42
     cervical
    0.41
     TPR
    0.41
     é
    0.40
     né
    0.40
    asy
    0.40
    POSITIVE LOGITS
     চুক্ত
    0.54
     শিক্ষার্থীদের
    0.48
     เพื่อ
    0.46
     പുതു
    0.46
    新たに
    0.46
    ကြောင်း
    0.45
     ব্যবহারের
    0.44
     ವರ್ಗ
    0.44
     유지
    0.44
    鹘
    0.43
    Activations Density 0.000%

    No Known Activations