© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76801
    Prev
    Next
    INDEX
    Explanations

    Windows names, C++, Windows paths

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

    The neuron is detecting segments of C/C++ source code—especially type and identifier tokens in function declarations and signatures.

    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
    strlen
    -0.79
     strlen
    -0.77
    otsu
    -0.75
    IBAction
    -0.74
    strcmp
    -0.74
    strncpy
    -0.73
    Those
    -0.71
     hız
    -0.71
    strcpy
    -0.69
    CTYPE
    -0.69
    POSITIVE LOGITS
     Clown
    0.90
    licates
    0.83
     wc
    0.82
    wist
    0.79
    wcs
    0.79
     voluntarios
    0.76
     Kiran
    0.75
    ཝ
    0.75
    moduleName
    0.73
     amphi
    0.73
    Activations Density 0.020%

    No Known Activations