© 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. 10-GEMMASCOPE-RES-131K
    4. 124155
    Prev
    Next
    INDEX
    Explanations

    code block openers

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

    The neuron fires on embedded code delimiters (e.g. “<?” and “@”) indicating server‐side/script code blocks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ,
    -1.93
    empio
    -1.63
     of
    -1.52
     its
    -1.52
    </b>
    -1.52
    );
    -1.50
     that
    -1.45
    We
    -1.39
     日期
    -1.38
     및
    -1.30
    POSITIVE LOGITS
     only
    1.70
     first
    1.59
    ڧ
    1.49
     stesse
    1.47
    Tecnologia
    1.47
     शुर
    1.44
    はこんな感じ
    1.42
     scoprire
    1.42
    Cuidado
    1.37
    sivamente
    1.36
    Activations Density 0.008%

    No Known Activations