© 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. 92296
    Prev
    Next
    INDEX
    Explanations

    HPP_INCLUDED headers

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

    The neuron is keyed to spotting boilerplate/license‐style code fragments—e.g. comment asterisks, preprocessor tokens, “use,” “License,” and the punctuation that typically appears in software‐license headers.

    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
    ınca
    -0.82
     ministra
    -0.74
    alamualaikum
    -0.72
    Them
    -0.72
     москва
    -0.71
     hän
    -0.71
    Koh
    -0.70
    ઝ
    -0.70
    產生
    -0.70
     Img
    -0.70
    POSITIVE LOGITS
     přij
    0.83
     tumbuhan
    0.81
    ,“
    0.78
     مواليد
    0.75
     bv
    0.75
    fiore
    0.75
    ecirc
    0.75
    拯救
    0.75
    jaja
    0.74
    ffindor
    0.73
    Activations Density 0.003%

    No Known Activations