© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38953
    Prev
    Next
    INDEX
    Explanations

    case statements and programming questions

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

    The neuron fires on the “|” branch‐delimiter (and its associated numeric indent token) in code, i.e. the pipe that introduces each case or match clause.

    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
     would
    -1.39
     for
    -1.37
     while
    -1.27
    izioni
    -1.23
     and
    -1.21
     Those
    -1.20
     as
    -1.19
    yoruz
    -1.19
     ville
    -1.13
    ——”
    -1.13
    POSITIVE LOGITS
    *
    1.30
     erneu
    1.21
    ...
    1.16
     nhung
    1.15
     anything
    1.11
    一个小
    1.10
    ‘
    1.10
    –
    1.09
    idk
    1.08
     frecuentes
    1.08
    Activations Density 0.001%

    No Known Activations