© 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. 45372
    Prev
    Next
    INDEX
    Explanations

    programming IO

    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
    and
    -3.11
    تیجه
    -3.08
    of
    -3.06
    E
    -3.05
    ڧ
    -2.69
    R
    -2.63
    O
    -2.63
     halben
    -2.59
    which
    -2.56
    $,
    -2.48
    POSITIVE LOGITS
    翃
    3.55
    푔
    3.11
     geniş
    2.84
     superstar
    2.64
     crée
    2.63
     tumultuous
    2.53
     recopila
    2.48
     exceptionally
    2.45
     alcuni
    2.42
     remarkably
    2.42
    Activations Density 0.003%

    No Known Activations