© 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. 10-GEMMASCOPE-RES-131K
    7. 29131
    Prev
    Next
    INDEX
    Explanations

    travis-ci or .ci domains

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

    The neuron activates on occurrences of the exact token “ci” (e.g. as in “ehci,” “travis-ci,” etc.).

    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
    In
    -4.09
    in
    -3.14
    on
    -2.84
     Roughly
    -2.73
     Traditionally
    -2.73
    2
    -2.69
     Undoubtedly
    -2.63
    在這
    -2.58
    al
    -2.56
    ра
    -2.55
    POSITIVE LOGITS
    s
    5.50
    ci
    3.05
    涠
    2.81
    廰
    2.80
    亖
    2.73
    嗩
    2.69
    铼
    2.67
    bowl
    2.67
    cised
    2.66
    놋
    2.64
    Activations Density 0.016%

    No Known Activations