© 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. 34-GEMMASCOPE-RES-131K
    7. 78075
    Prev
    Next
    INDEX
    Explanations

    inside and outside locations

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

    The neuron turns on for content‐bearing words—mostly nouns, verbs, and other substantive terms—rather than for common function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Interior
    -2.25
    interior
    -2.11
     Interior
    -2.11
     interior
    -1.74
     INTERIOR
    -1.69
     interiors
    -1.68
     Interiors
    -1.61
    INTERIOR
    -1.48
     Exterior
    -1.25
    Internal
    -1.16
    POSITIVE LOGITS
    Copia
    0.91
    eaus
    0.90
     outside
    0.88
    弱い
    0.86
     inside
    0.85
    reported
    0.79
    valued
    0.78
     rempliss
    0.78
    зар
    0.77
    场地
    0.77
    Activations Density 0.042%

    No Known Activations