© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7513
    Prev
    Next
    INDEX
    Explanations

    web development and programming

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

    The neuron flags tokens that look like code‐style paths or file‐system references (e.g. strings with slashes, dots, and directory names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    file paths and directory separators in technical or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    structured technical references such as code/config paths, environment variables, and numbered sections or figures in documentation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yesters
    0.72
     Në
    0.70
    दून
    0.66
    ceedings
    0.65
     Cnemidophorus
    0.65
    ॅन
    0.64
     Canadá
    0.64
     extinguishing
    0.64
    ంచరీలు
    0.63
    udades
    0.63
    POSITIVE LOGITS
    Config
    0.67
    自身の
    0.66
    Get
    0.63
    App
    0.61
    恕
    0.61
    getQuery
    0.61
    Toast
    0.60
     কর্তৃক
    0.59
    G
    0.59
    тово
    0.58
    Activations Density 0.133%

    No Known Activations