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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68970
    Prev
    Next
    INDEX
    Explanations

    data columns: customer, min, nature, user

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

    The neuron fires on tokens from code identifiers or type names that use uppercase letters or CamelCase.

    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
     Offisielt
    -1.07
     interference
    -0.91
    PAIGN
    -0.88
     дефек
    -0.84
     leafy
    -0.82
     něj
    -0.81
    ménage
    -0.81
    麸
    -0.79
    帖最后由
    -0.77
    aibo
    -0.75
    POSITIVE LOGITS
    dra
    0.90
    节点
    0.89
     Lotte
    0.89
    tarjeta
    0.85
     lác
    0.85
    Uz
    0.83
    getRandom
    0.81
     Reng
    0.80
    sugges
    0.79
    receta
    0.79
    Activations Density 0.039%

    No Known Activations