© 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. 47093
    Prev
    Next
    INDEX
    Explanations

    Mexican cuisine, vehicles, or spatial descriptions

    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
    Negative Logits
    ัตว์
    -0.82
    明白了
    -0.81
    typer
    -0.80
     Holistic
    -0.77
     extensão
    -0.77
    Verlag
    -0.74
    吧
    -0.73
    FontAwesomeIcon
    -0.73
    徨
    -0.73
     obszar
    -0.72
    POSITIVE LOGITS
     currently
    0.95
     Recently
    0.92
    Currently
    0.89
    Recently
    0.87
     récit
    0.83
     luminos
    0.83
     Currently
    0.82
    lari
    0.81
     Exposure
    0.81
    currently
    0.80
    Activations Density 0.005%

    No Known Activations