© 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. 193116
    Prev
    Next
    INDEX
    Explanations

    follow

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

    life cycle and relationships

    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
    Negative Logits
    ጇ
    0.53
    ąż
    0.49
     privilégi
    0.48
    któ
    0.48
    ukannya
    0.48
    췄
    0.47
     तुम्हाला
    0.46
     অঞ্চ
    0.45
    이트
    0.45
    樊
    0.45
    POSITIVE LOGITS
     Shu
    0.49
     Adobe
    0.47
     Quad
    0.47
     Urban
    0.46
     the
    0.46
     Agama
    0.45
     GI
    0.45
     Shine
    0.45
     Trend
    0.44
     SH
    0.44
    Activations Density 0.000%

    No Known Activations