© 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. 113876
    Prev
    Next
    INDEX
    Explanations

    renovation and improvement

    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
    s
    -1.76
    喽
    -1.71
     these
    -1.66
     any
    -1.51
    ).
    -1.44
    atshirt
    -1.42
     provides
    -1.40
    even
    -1.38
     Even
    -1.36
    上门
    -1.35
    POSITIVE LOGITS
    samt
    1.72
     complètement
    1.65
     makeover
    1.61
     biografia
    1.61
     秘密
    1.58
    mädchen
    1.57
     juc
    1.57
     regata
    1.55
     protesta
    1.53
     faca
    1.53
    Activations Density 0.048%

    No Known Activations