© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12179
    Prev
    Next
    INDEX
    Explanations

    PE teachers, area, persons

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

    The neuron fires on tokens that appear in code‐comment metadata headers and declarations (e.g. “File Name,” “Created,” version/license strings, function entry labels, etc.).

    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
     eyew
    -0.70
    門
    -0.70
    دخ
    -0.66
     Acquire
    -0.66
    Crumb
    -0.64
    邯
    -0.64
    čních
    -0.62
    AuthContext
    -0.62
    keyp
    -0.60
     Broke
    -0.60
    POSITIVE LOGITS
    Bindable
    0.80
    ípio
    0.78
     klik
    0.71
     missiles
    0.69
    RICT
    0.69
     حض
    0.68
     Olin
    0.68
     Steele
    0.67
     Orchestra
    0.67
    DRO
    0.67
    Activations Density 0.078%

    No Known Activations