© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62636
    Prev
    Next
    INDEX
    Explanations

    string and QString literals

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

    The neuron consistently fires on occurrences of the identifier “string” (e.g. std::string, QString, etc.) in code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ylvania
    -0.92
    Ev
    -0.81
    ospels
    -0.78
     dobr
    -0.78
    Serum
    -0.77
     Exteriores
    -0.77
     cưới
    -0.76
    Mathias
    -0.76
    koc
    -0.75
     vlož
    -0.75
    POSITIVE LOGITS
     number
    0.86
     cleared
    0.79
    number
    0.77
    ("
    0.73
    Literal
    0.71
    зулта
    0.71
    穿搭
    0.70
    boost
    0.70
    (<
    0.70
    *}\
    0.69
    Activations Density 0.009%

    No Known Activations