© 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. 2196
    Prev
    Next
    INDEX
    Explanations

    code and questions

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

    The neuron activates on numeric literals (sequences of digits) in code.

    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
    isip
    -0.82
    nable
    -0.79
    掘
    -0.79
    യി
    -0.79
     vaikka
    -0.78
    mā
    -0.77
    ndry
    -0.76
     uhd
    -0.75
    计
    -0.75
    cteurs
    -0.75
    POSITIVE LOGITS
    eq
    0.76
    sS
    0.69
    яв
    0.69
     Writings
    0.68
     Stiles
    0.68
    人類
    0.67
     Sentences
    0.67
     جدًا
    0.66
     DAMAGES
    0.66
     worden
    0.66
    Activations Density 0.022%

    No Known Activations