© 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. 82924
    Prev
    Next
    INDEX
    Explanations

    code declarations and paths

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

    The neuron fires on programming‐language tokens and syntax (e.g. keywords like “public,” “final,” file/form identifiers like “proto,” and delimiters like “<” or “///”), i.e. code-specific vocabulary.

    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
    ştir
    -0.85
    ामी
    -0.79
     Matériau
    -0.78
     najbolj
    -0.77
     Dunham
    -0.77
    ۤ
    -0.77
     غرفة
    -0.75
    hadow
    -0.75
     Tuttavia
    -0.75
    畠
    -0.74
    POSITIVE LOGITS
     If
    0.88
    guint
    0.85
     optional
    0.82
     Whether
    0.81
     wächst
    0.78
     kolejny
    0.75
     like
    0.75
    ět
    0.74
    <code>
    0.73
    JsonInclude
    0.72
    Activations Density 0.001%

    No Known Activations