© 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. 144691
    Prev
    Next
    INDEX
    Explanations

    states after common words

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

    family and company 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
    Not in Any Lists

    No Comments

    Negative Logits
     R
    0.52
     Necklace
    0.49
     Histogram
    0.49
     necklace
    0.48
     spiral
    0.48
     Tournament
    0.48
     cultivator
    0.48
    -
    0.48
     B
    0.47
    =
    0.47
    POSITIVE LOGITS
    ﾅ
    0.53
    ﾆ
    0.52
    狯
    0.50
     он
    0.49
    НЯ
    0.47
    İL
    0.47
     Оси
    0.47
    KOM
    0.46
     скон
    0.46
    玤
    0.46
    Activations Density 0.000%

    No Known Activations