© 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. 21700
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by punctuation

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

    This neuron fires on long identifier‐style tokens in code or config—e.g. names made up of multiple words joined by dots, underscores, or CamelCase.

    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
     '
    -2.83
    不错
    -2.55
     was
    -2.47
    偏偏
    -2.31
     and
    -2.27
     lament
    -2.22
     impec
    -2.19
     quando
    -2.17
    很少
    -2.13
     是
    -2.11
    POSITIVE LOGITS
    .
    3.98
    <bos>
    3.38
    酲
    2.94
    ,’
    2.89
    趼
    2.84
    ftrag
    2.80
     robić
    2.75
    錒
    2.63
    醞
    2.61
     ")
    2.59
    Activations Density 0.259%

    No Known Activations