© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128687
    Prev
    Next
    INDEX
    Explanations

    references to specific items

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

    The neuron appears never to activate on any of these texts, suggesting it does not detect any specific pattern (i.e. it’s effectively inactive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     if
    -2.33
     For
    -2.03
     is
    -1.97
    hiva
    -1.88
    ↵↵
    -1.86
    erializer
    -1.86
    }),
    -1.82
     it
    -1.76
    ciato
    -1.73
    agliari
    -1.69
    POSITIVE LOGITS
     épais
    2.23
     zorro
    1.91
     incroy
    1.88
     että
    1.84
     devraient
    1.80
     sorts
    1.80
     sanno
    1.78
     déchir
    1.77
     récupérer
    1.76
    ter
    1.74
    Activations Density 0.022%

    No Known Activations