© 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. 71484
    Prev
    Next
    INDEX
    Explanations

    code structures and fields

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

    This neuron detects numeric literals (number tokens) 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
     while
    -1.13
     istimewa
    -1.10
     Schrifts
    -1.07
    lloworld
    -1.07
     Hauptstadt
    -1.04
    źnie
    -1.03
    xspace
    -1.02
     Weisheit
    -1.02
    AutoModerator
    -1.01
     Gedichte
    -1.00
    POSITIVE LOGITS
    ところに
    1.02
    Raquel
    0.99
    萼
    0.99
    ordnungen
    0.95
    Автор
    0.95
     facteurs
    0.94
    不錯
    0.94
     lejos
    0.92
    unn
    0.92
    ित्र
    0.92
    Activations Density 0.002%

    No Known Activations