© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172191
    Prev
    Next
    INDEX
    Explanations

    mailing and notice

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

    code blocks and special characters

    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
    <0x0D>
    0.55
     系
    0.48
     pupils
    0.46
     chatter
    0.46
     zare
    0.46
     wrapper
    0.44
     zio
    0.44
     einigen
    0.44
     BOW
    0.43
    zept
    0.43
    POSITIVE LOGITS
     نشده
    0.50
     ویت
    0.47
     predecess
    0.47
    𒌋
    0.46
     عر
    0.46
     ristrutt
    0.46
     دلیل
    0.45
     renovating
    0.45
     مخطط
    0.45
     здрав
    0.44
    Activations Density 0.001%

    No Known Activations