© 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. 22-GEMMASCOPE-RES-131K
    7. 16412
    Prev
    Next
    INDEX
    Explanations

    parentheses and code structures

    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
    がありますが
    -1.61
    もありますが
    -1.58
    もあります
    -1.58
    haviours
    -1.52
    Zubereitung
    -1.52
     作り方
    -1.44
    Preparazione
    -1.36
    pleft
    -1.35
    もあって
    -1.34
     corporativa
    -1.34
    POSITIVE LOGITS
    為に
    1.52
    _
    1.48
     and
    1.46
    了些
    1.45
    0
    1.29
    ;
    1.23
    ara
    1.20
    ほうが
    1.18
     a
    1.17
    ことが
    1.16
    Activations Density 0.002%

    No Known Activations