© 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. 30068
    Prev
    Next
    INDEX
    Explanations

    commands, technical questions, or system status

    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
     insp
    -0.82
    Edit
    -0.72
    Snackbar
    -0.71
     neon
    -0.69
    inspire
    -0.68
     ì
    -0.68
     manufacturer
    -0.68
     INSPIRE
    -0.67
    财经
    -0.67
     Neon
    -0.67
    POSITIVE LOGITS
     firent
    0.87
    =+
    0.83
    toJSONString
    0.82
    🦮
    0.79
    southeast
    0.79
    tokens
    0.78
     tokens
    0.77
     menjal
    0.77
     fizer
    0.77
    的で
    0.76
    Activations Density 0.010%

    No Known Activations