© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86227
    Prev
    Next
    INDEX
    Explanations

    his and hers jewelry

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

    This neuron activates on specialized technical or scientific jargon—uncommon domain-specific vocabulary.

    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
     with
    -2.03
     time
    -1.82
     who
    -1.78
     would
    -1.76
     should
    -1.72
     have
    -1.65
     could
    -1.63
     regarding
    -1.62
     and
    -1.60
     or
    -1.59
    POSITIVE LOGITS
    得好
    1.52
     !!!!!
    1.49
     exatamente
    1.47
    了不少
    1.46
     !!!!
    1.45
    commonly
    1.45
     arrivent
    1.44
     jeudi
    1.42
     .......
    1.38
     solamente
    1.37
    Activations Density 0.155%

    No Known Activations