© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9074
    Prev
    Next
    INDEX
    Explanations

    cout << or cerr <<

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

    This neuron strongly responds to non-standard tokens such as symbol sequences (e.g. “<<”, “\n”) and capitalized identifiers or proper names, i.e. tokens containing uppercase or punctuation characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arabic
    0.57
    nts
    0.57
    {},
    0.57
    readLine
    0.56
     dana
    0.56
    indexBuffer
    0.56
    printf
    0.55
    scanf
    0.55
    ISTA
    0.55
    ESP
    0.55
    POSITIVE LOGITS
     <<
    1.09
    <<
    0.80
     assumptions
    0.63
     <<"
    0.63
     permeate
    0.63
    ()<<
    0.62
    )<<
    0.62
    <<"
    0.62
     Assumptions
    0.61
     steeply
    0.61
    Activations Density 0.012%

    No Known Activations