© 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. 22-GEMMASCOPE-RES-131K
    7. 11031
    Prev
    Next
    INDEX
    Explanations

    Configuration parameters or settings

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

    The neuron fires on isolated code‐style identifiers—variable, parameter, constant, or tag names (e.g. config keys, function or type names) rather than normal prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.80
     verur
    -1.41
    さぁ
    -1.41
     riserv
    -1.32
     or
    -1.31
    づけ
    -1.29
    つづく
    -1.27
    ほら
    -1.27
    あー
    -1.27
     impegn
    -1.27
    POSITIVE LOGITS
    などが
    1.76
    所以在
    1.39
    などを
    1.39
    <bos>
    1.37
    それも
    1.36
    が
    1.35
    但却
    1.34
    や
    1.34
    それは
    1.34
    もある
    1.29
    Activations Density 0.108%

    No Known Activations