© 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. 22-GEMMASCOPE-RES-131K
    7. 25182
    Prev
    Next
    INDEX
    Explanations

    Q: or questions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is effectively inactive and does not detect any meaningful token patterns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -0.98
     whofe
    -0.94
     they
    -0.94
     ткань
    -0.94
     this
    -0.89
    FormUrlEncoded
    -0.89
    genza
    -0.87
     batas
    -0.86
     even
    -0.85
     кос
    -0.83
    POSITIVE LOGITS
    ený
    1.23
    Hilsen
    1.13
    ujący
    0.96
     umožňuje
    0.96
    origine
    0.93
    过头
    0.91
     ahora
    0.90
     tých
    0.90
     proceso
    0.89
     禁止
    0.88
    Activations Density 0.000%

    No Known Activations