© 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. 72878
    Prev
    Next
    INDEX
    Explanations

    computation or code expressions

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

    The neuron fires on programming identifiers or tokens containing “expr” (e.g. “expression,” “Expr,” “expr”).

    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
    VENT
    -1.02
    argue
    -1.00
    Uber
    -0.99
     firft
    -0.98
    不同
    -0.97
     鸡蛋
    -0.96
    вна
    -0.94
    klassi
    -0.94
    direktor
    -0.93
     Illus
    -0.93
    POSITIVE LOGITS
     our
    1.09
     graciosas
    1.09
     anything
    1.09
     or
    1.05
     computation
    1.05
     liefern
    1.02
    颧
    1.01
     aquello
    1.00
     antioxidant
    0.99
     expression
    0.99
    Activations Density 0.039%

    No Known Activations