© 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. 166567
    Prev
    Next
    INDEX
    Explanations

    Memorial Day

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

    state secretary, zone movement, end of turn

    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
    borhood
    0.54
    ري
    0.51
    譏
    0.51
    薬
    0.49
    punten
    0.49
    sekten
    0.48
    тию
    0.47
     부담
    0.47
     இஸ்
    0.45
    禱
    0.45
    POSITIVE LOGITS
    😊
    0.52
    an
    0.52
    ore
    0.49
    a
    0.49
    ‪‬
    0.48
    </blockquote>
    0.48
     diversified
    0.46
    ano
    0.46
     indifferent
    0.46
    4
    0.45
    Activations Density 0.001%

    No Known Activations