© 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. 6959
    Prev
    Next
    INDEX
    Explanations

    pin

    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
     you
    -3.27
    ↵↵
    -3.02
     —
    -2.66
    :
    -2.45
    ’
    -2.44
    ↵↵↵
    -2.39
     can
    -2.30
    .
    -2.25
    —
    -2.17
    ,’
    -2.11
    POSITIVE LOGITS
    魮
    2.67
    ୫
    2.52
    騭
    2.50
    ᛬
    2.44
    櫺
    2.42
    鮠
    2.41
    豨
    2.34
    哙
    2.16
    kwür
    2.16
    zember
    2.16
    Activations Density 0.012%

    No Known Activations