© 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. 22-GEMMASCOPE-RES-131K
    7. 27662
    Prev
    Next
    INDEX
    Explanations

    code and mathematical expressions

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

    The neuron lights up on uncommon, domain-specific tokens—especially programming identifiers or technical/scientific jargon.

    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
    MONGO
    -1.00
    ühnen
    -0.96
     mengumumkan
    -0.94
    setNome
    -0.93
     membag
    -0.93
    Lama
    -0.90
    relógio
    -0.86
    gunakan
    -0.85
    くなりました
    -0.85
    所以在
    -0.82
    POSITIVE LOGITS
     ziren
    1.04
    ógico
    0.97
    かれている
    0.91
     families
    0.88
     Altos
    0.84
     Blouse
    0.84
    ढ़
    0.82
     there
    0.82
     квартиры
    0.81
    跑了
    0.81
    Activations Density 0.030%

    No Known Activations