© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15480
    Prev
    Next
    INDEX
    Explanations

    conditional programming logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     všechny
    -1.71
    杙
    -1.63
    想了
    -1.63
    ︲
    -1.62
     bénéficiaire
    -1.61
     a
    -1.59
    一定的
    -1.57
     鱼
    -1.55
    靫
    -1.55
    ’，
    -1.55
    POSITIVE LOGITS
     but
    2.16
    It
    2.13
    There
    1.70
    The
    1.70
    When
    1.68
    If
    1.68
     vostra
    1.68
     recensione
    1.66
    Because
    1.66
    That
    1.66
    Activations Density 0.004%

    No Known Activations