© 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. 69915
    Prev
    Next
    INDEX
    Explanations

    year numbers followed by "members" or "include"

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

    The neuron specializes in spotting comment‐style delimiter lines (e.g. sequences of slashes, equals signs, dashes, etc.) used to separate or banner sections in source code.

    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
     Godfrey
    -0.76
    Decorated
    -0.73
     ר
    -0.69
    製
    -0.69
    getInteger
    -0.69
     polymeric
    -0.68
    glMatrix
    -0.67
    Marshal
    -0.67
    الا
    -0.66
    cznej
    -0.66
    POSITIVE LOGITS
     Anglia
    0.76
    innerText
    0.74
    ریز
    0.70
    Verbose
    0.69
     glor
    0.68
    volumes
    0.67
     abhor
    0.67
     xii
    0.66
    iß
    0.64
     Alex
    0.62
    Activations Density 0.406%

    No Known Activations