© 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. 90437
    Prev
    Next
    INDEX
    Explanations

    code method calls

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

    This neuron primarily detects the dot (“.”) in code, i.e. object-member or method-call syntax.

    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
    liese
    -0.79
    bereit
    -0.78
     canceled
    -0.78
    帯
    -0.75
     injecting
    -0.75
     fri
    -0.74
    UNDP
    -0.74
    cą
    -0.73
    vesen
    -0.72
    ')(
    -0.71
    POSITIVE LOGITS
     através
    0.84
    țele
    0.76
    ätz
    0.73
     Wasch
    0.73
    getId
    0.71
     = 
    0.71
     rádio
    0.71
    getTag
    0.71
    endl
    0.70
    VISIBLE
    0.70
    Activations Density 0.004%

    No Known Activations