© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78096
    Prev
    Next
    INDEX
    Explanations

    string and memory functions

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

    The neuron detects code identifiers for C standard library routines (especially string‐ and memory‐handling functions like “str*” and “mem*”).

    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
     който
    -0.77
     Silt
    -0.77
    hā
    -0.76
     silt
    -0.75
     antiquities
    -0.73
    今は
    -0.73
    現在は
    -0.70
    Structured
    -0.70
     Sahib
    -0.70
     Leth
    -0.70
    POSITIVE LOGITS
    strcpy
    1.02
    strstr
    0.97
    memcpy
    0.86
     copies
    0.85
    str
    0.81
    strncpy
    0.79
     copying
    0.77
     str
    0.76
     עוב
    0.76
    Seguir
    0.75
    Activations Density 0.022%

    No Known Activations