© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65743
    Prev
    Next
    INDEX
    Explanations

    code symbols and punctuation

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

    This neuron detects standalone underscore tokens (the “_” placeholder or wildcard) in code.

    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
     only
    -1.27
     there
    -1.10
     farol
    -1.03
     lanterna
    -0.98
     marcos
    -0.98
     ready
    -0.98
     things
    -0.98
    ⊶
    -0.96
     need
    -0.96
     not
    -0.95
    POSITIVE LOGITS
     préserver
    1.11
     indien
    1.00
     dépos
    0.96
     mať
    0.94
     scammed
    0.93
     pemuda
    0.92
     ekonomi
    0.91
    🥋
    0.91
     skriva
    0.91
     skriver
    0.90
    Activations Density 0.002%

    No Known Activations