© 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. 114134
    Prev
    Next
    INDEX
    Explanations

    Mac as a prefix or name part

    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
    狁
    -2.91
    嵓
    -2.88
    蚡
    -2.77
    瑨
    -2.75
    亖
    -2.73
    鶿
    -2.64
    甃
    -2.63
    </h3>
    -2.59
    
    -2.58
    髎
    -2.56
    POSITIVE LOGITS
    In
    4.88
     &
    3.13
    ’
    3.05
    </b>
    2.66
    f
    2.58
    d
    2.53
     dalam
    2.52
    as
    2.47
     в
    2.47
    b
    2.45
    Activations Density 0.030%

    No Known Activations