© 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. 10-GEMMASCOPE-RES-131K
    7. 113307
    Prev
    Next
    INDEX
    Explanations

    code, string, and sqlite operations

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

    string manipulation functions and operations in programming code, particularly `strcpy`, `strcat`, and related C string functions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on identifiers starting with “str” (especially C string functions like strcpy, strcat, and strcasecmp).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    This
    -2.75
    There
    -2.64
     With
    -2.58
    That
    -2.55
     burgeoning
    -2.47
    These
    -2.44
    While
    -2.42
     Surprisingly
    -2.41
    Those
    -2.41
    With
    -2.41
    POSITIVE LOGITS
     betreffende
    2.75
     the
    2.56
    棐
    2.45
    ⼰
    2.45
     investimento
    2.39
     remainder
    2.39
    糨
    2.39
    ჻
    2.39
     bedien
    2.38
    粜
    2.38
    Activations Density 0.000%

    No Known Activations