© 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. 68551
    Prev
    Next
    INDEX
    Explanations

    laws and requirements

    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
    Negative Logits
    ᐠ
    -1.66
    \
    -1.66
     

    -1.61
     \
    -1.59
    ⚥
    -1.52
     .\
    -1.50
    $).
    -1.49
     PUSTAKA
    -1.46
    </em>
    -1.43
     correspon
    -1.43
    POSITIVE LOGITS
    焄
    1.78
    when
    1.68
    勦
    1.66
     kualitas
    1.64
    PTEMBER
    1.61
    壜
    1.57
     kiedyś
    1.55
    as
    1.54
    你看
    1.52
     meestal
    1.52
    Activations Density 0.032%

    No Known Activations