© 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. 74942
    Prev
    Next
    INDEX
    Explanations

    variable declaration

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

    The neuron fires on code identifiers (variable, function, and type names) rather than ordinary words.

    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
     хотя
    -0.91
    llama
    -0.89
    edere
    -0.89
    יבות
    -0.88
     Dend
    -0.88
    historie
    -0.88
    Andere
    -0.87
    maestro
    -0.87
    loggen
    -0.87
     recientes
    -0.84
    POSITIVE LOGITS
     esetén
    0.90
     If
    0.89
    ров
    0.87
     if
    0.85
     próprio
    0.84
     nélkül
    0.83
     escritório
    0.83
     colorWith
    0.82
    álva
    0.82
     prowadzi
    0.82
    Activations Density 0.013%

    No Known Activations