© 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. 225427
    Prev
    Next
    INDEX
    Explanations

    white paper

    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
    st
    0.51
    تا
    0.49
    ت
    0.47
    :
    0.45
     anomal
    0.44
     Inferno
    0.44
     Alumni
    0.42
     Aerial
    0.42
    -
    0.42
     Coupling
    0.42
    POSITIVE LOGITS
     سایټ
    0.50
     చి
    0.46
     用户
    0.46
     PARTY
    0.46
    ającym
    0.46
     স্টেশন
    0.44
     விரிவா
    0.44
    식회사
    0.44
     brisket
    0.43
     পার্টি
    0.43
    Activations Density 0.004%

    No Known Activations