© 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. 34-GEMMASCOPE-RES-131K
    7. 12282
    Prev
    Next
    INDEX
    Explanations

    struct field definitions

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

    The neuron activates on programming identifiers—names of variables, functions, types, fields, etc.—in source 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_34/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
    ḿ
    -0.89
     Gebet
    -0.89
     ajuta
    -0.82
     Öffnungszeiten
    -0.82
     Geschichts
    -0.81
    }],
    -0.81
    ::*;
    -0.80
     già
    -0.80
    ()
    -0.79
    ğimiz
    -0.79
    POSITIVE LOGITS
    vocable
    0.98
    [
    0.96
    DING
    0.94
     scuro
    0.92
     próprias
    0.92
    ريس
    0.90
    Информация
    0.90
    Ň
    0.90
    Falta
    0.90
    valid
    0.90
    Activations Density 0.011%

    No Known Activations