© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7052
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on technical code‐style identifiers—library or module names, file/path fragments, and other programming jargon (e.g. hyphenated or underscored component names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    IService
    0.56
    iatrics
    0.55
     내부
    0.55
     Platforms
    0.55
    InputElement
    0.54
     '../../
    0.53
    லத்தில்
    0.53
    AppState
    0.53
     eğitimi
    0.53
    igene
    0.52
    POSITIVE LOGITS
    插件
    0.79
    开源
    0.70
     jquery
    0.67
     Easy
    0.63
    awesome
    0.61
     jq
    0.60
     plugin
    0.59
    🏆
    0.59
    jquery
    0.58
     [![
    0.58
    Activations Density 0.158%

    No Known Activations