© 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. 34-GEMMASCOPE-RES-131K
    7. 62717
    Prev
    Next
    INDEX
    Explanations

    code parsing and structure

    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_34/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
     similar
    -0.96
    だな
    -0.92
    mamış
    -0.91
    crição
    -0.88
     analogous
    -0.85
     Etc
    -0.84
    clusão
    -0.84
     måte
    -0.84
     Calibration
    -0.81
    ๘
    -0.81
    POSITIVE LOGITS
    ，
    0.91
    ẕ
    0.87
     lẫn
    0.87
    '},
    0.85
     przypadku
    0.82
    。
    0.82
     langen
    0.81
    '].
    0.81
    }}},
    0.81
    }{@
    0.81
    Activations Density 0.147%

    No Known Activations