© 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. 93951
    Prev
    Next
    INDEX
    Explanations

    serotonin transporter promoter

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

    programming code and markup language elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on programming-style tokens—identifiers, keywords, symbols, and other code elements—rather than natural-language words.

    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
    plage
    -0.85
    Ranges
    -0.75
    の新
    -0.73
    Establish
    -0.73
    atable
    -0.69
    fej
    -0.69
     групи
    -0.69
    ieb
    -0.68
    ultati
    -0.68
    chromium
    -0.68
    POSITIVE LOGITS
    arca
    0.71
    ம
    0.70
    xmlns
    0.66
     Spam
    0.66
    新聞
    0.66
    érape
    0.66
    мпа
    0.64
    ար
    0.64
    ską
    0.62
    LEGO
    0.62
    Activations Density 0.068%

    No Known Activations