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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59535
    Prev
    Next
    INDEX
    Explanations

    code delimiters or structured text

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

    The neuron flags programming‐style tokens—things like include directives, file‐extension markers (e.g. “.h”), braces, version numbers, and other code/syntax elements.

    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
    Cyto
    -0.66
     なる
    -0.64
    zov
    -0.64
     FOV
    -0.63
     UUID
    -0.62
    Checked
    -0.62
    弥
    -0.62
    ТИ
    -0.60
    回头
    -0.60
    inna
    -0.60
    POSITIVE LOGITS
    adden
    0.75
    getFont
    0.74
    milliseconds
    0.71
    dotta
    0.69
    เต
    0.67
     iconLine
    0.66
    机械
    0.66
     Noch
    0.65
     summit
    0.65
    サル
    0.65
    Activations Density 0.064%

    No Known Activations