© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1687
    Prev
    Next
    INDEX
    Explanations

    git commands, code, date, tags

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

    The neuron detects tokens that indicate code or command elements—programming-language, module/primitive, or tooling identifiers and other code-related keywords.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    他们的
    0.30
     их
    0.30
     Rien
    0.30
     जिलों
    0.28
    秾
    0.28
     असंख्य
    0.28
    ސ
    0.28
     इसी
    0.28
     franch
    0.27
     ljub
    0.27
    POSITIVE LOGITS
    ？
    0.33
    そもそも
    0.32
    を作る
    0.32
    。
    0.32
    overall
    0.32
    containsKey
    0.31
    (),
    0.31
    involved
    0.31
     изначально
    0.31
    ต้องการ
    0.31
    Activations Density 0.181%

    No Known Activations