© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73955
    Prev
    Next
    INDEX
    Explanations

    programming commands and conjunctions

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

    The neuron fires on code identifiers—names of functions, modules, or include-file tokens in source text.

    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
    ll
    -3.30
    la
    -3.27
    be
    -3.00
    q
    -2.91
    end
    -2.89
    at
    -2.88
    ya
    -2.75
    li
    -2.75
    os
    -2.73
    r
    -2.69
    POSITIVE LOGITS
    ︐
    3.17
    錞
    2.45
    鲧
    2.34
     direta
    2.28
    lossians
    2.27
    狁
    2.27
     econômica
    2.25
    riculares
    2.19
    vgili
    2.17
    鹟
    2.16
    Activations Density 0.006%

    No Known Activations