© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    checkbox state

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

    This neuron specializes in spotting programming identifiers (e.g. method and class names, API calls, and underscore‐ or CamelCase tokens) within code snippets.

    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
     ppm
    -0.85
    angun
    -0.76
    MeV
    -0.70
     resigned
    -0.69
     Gleaner
    -0.69
     vervangen
    -0.68
    頃の
    -0.68
     wzi
    -0.68
    бою
    -0.68
    われています
    -0.68
    POSITIVE LOGITS
    isChecked
    1.09
    setChecked
    0.95
     compound
    0.92
     isChecked
    0.89
     grupa
    0.88
     CheckBox
    0.82
    ابعة
    0.81
     Compound
    0.79
    晨
    0.75
     aparat
    0.75
    Activations Density 0.007%

    No Known Activations