© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92193
    Prev
    Next
    INDEX
    Explanations

    string manipulation in code

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

    The neuron fires on programming‐language tokens—identifiers (variable or method names) and string literals—rather than ordinary English words.

    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
     successful
    -0.96
     and
    -0.94
     being
    -0.90
     đầm
    -0.88
     successfully
    -0.85
     bữa
    -0.81
     having
    -0.81
     Successfully
    -0.75
    只能
    -0.73
     値下げ
    -0.73
    POSITIVE LOGITS
    substring
    1.24
    trim
    1.17
    replace
    1.16
     +
    1.12
     substring
    1.07
    replaceAll
    1.02
     replacements
    1.01
     +=
    0.98
     replacement
    0.94
     $+\
    0.94
    Activations Density 0.019%

    No Known Activations