© 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. 36685
    Prev
    Next
    INDEX
    Explanations

    e.g. qualifiers

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

    This neuron specializes in picking out tokens that occur inside parentheses (e.g. parenthetical terms or abbreviations).

    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
     from
    -1.35
     which
    -1.30
     it
    -1.27
     to
    -1.21
     that
    -1.16
     for
    -1.12
     when
    -1.12
     its
    -1.08
     in
    -1.07
     should
    -1.07
    POSITIVE LOGITS
    inemann
    1.06
     actionMode
    1.05
    indicates
    0.99
    ">(</
    0.98
     creazione
    0.97
    IMIENTO
    0.96
    appears
    0.95
    鲀
    0.94
     uniquement
    0.94
     Zustand
    0.93
    Activations Density 0.034%

    No Known Activations