© 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. 34-GEMMASCOPE-RES-131K
    7. 86852
    Prev
    Next
    INDEX
    Explanations

    multiple kinds, cost, seen, state

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

    The neuron fires on words and tokens that express numeric or quantitative information—counts, measurements, amounts, and related quantifiers.

    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
     addSubview
    -0.93
     retten
    -0.84
    rophi
    -0.84
    matics
    -0.83
    toJSONString
    -0.79
    bản
    -0.77
    ्रो
    -0.77
    Ꮞ
    -0.76
     dalej
    -0.76
    畦
    -0.75
    POSITIVE LOGITS
     proverbial
    0.96
     veritable
    0.84
     nothing
    0.83
     everything
    0.81
    層
    0.81
    Atlético
    0.80
    前后
    0.79
    层
    0.79
     like
    0.78
     never
    0.77
    Activations Density 0.008%

    No Known Activations