© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73329
    Prev
    Next
    INDEX
    Explanations

    post-translational modification; copyright; entities

    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
    There
    -3.28
    If
    -3.09
    With
    -2.83
    It
    -2.67
    When
    -2.56
    So
    -2.53
    there
    -2.45
    just
    -2.45
    Having
    -2.42
    first
    -2.41
    POSITIVE LOGITS
    rofl
    2.33
    疴
    2.23
     then
    2.11
     wherein
    2.11
     a
    2.06
     kulinar
    2.05
     at
    1.95
     gadis
    1.94
     bemerk
    1.94
     whereby
    1.89
    Activations Density 0.002%

    No Known Activations