© 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. 22-GEMMASCOPE-RES-131K
    4. 9301
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron detects header‐file names in #include directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    often
    -1.07
    here
    -0.99
    nical
    -0.98
    zl
    -0.95
    umbing
    -0.93
    our
    -0.92
    ecz
    -0.91
    p
    -0.91
    good
    -0.90
    gor
    -0.90
    POSITIVE LOGITS
     that
    1.14
     liburan
    0.97
    !")
    0.95
    !)
    0.95
    !");
    0.93
    !(
    0.93
    ?」
    0.92
     even
    0.91
    oría
    0.91
     because
    0.91
    Activations Density 0.029%

    No Known Activations