© 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. 60399
    Prev
    Next
    INDEX
    Explanations

    forum navigation

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

    The neuron fires on mentions of Linux distributions (their names and version numbers).

    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
     степени
    -0.74
     Esau
    -0.72
     saman
    -0.69
    getTime
    -0.69
     Förderung
    -0.68
    valente
    -0.67
     rayon
    -0.67
     Supremo
    -0.67
    tivi
    -0.66
    jon
    -0.65
    POSITIVE LOGITS
    pfn
    0.70
    منم
    0.66
    
    0.66
    Vine
    0.65
    ĝo
    0.65
     처
    0.65
     uneducated
    0.65
    bookId
    0.64
     ప
    0.64
    Numeric
    0.64
    Activations Density 0.067%

    No Known Activations