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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70661
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and punctuation

    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_22/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
     when
    -1.35
     for
    -1.18
     so
    -1.16
     also
    -1.14
     When
    -1.13
     just
    -1.10
     procedure
    -1.08
     to
    -1.06
     never
    -0.99
     quyến
    -0.97
    POSITIVE LOGITS
     dolu
    1.00
     Slab
    0.96
    ynthesis
    0.96
    tlement
    0.96
    |<
    0.95
    念头
    0.95
    Slab
    0.94
     manguera
    0.94
    legten
    0.94
     dn
    0.94
    Activations Density 0.007%

    No Known Activations