© 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. 2456
    Prev
    Next
    INDEX
    Explanations

    vendor license

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    HasOne
    -0.75
    よな
    -0.68
    дь
    -0.65
    ungkan
    -0.63
     Prizes
    -0.63
     amusing
    -0.61
     Horace
    -0.61
    reactivex
    -0.60
     advertise
    -0.60
    やろ
    -0.60
    POSITIVE LOGITS
    fuk
    0.94
    👴
    0.81
     bornes
    0.71
     fonctionnalités
    0.71
    uca
    0.71
    ripe
    0.71
     gerecht
    0.71
    👂
    0.70
    atle
    0.70
    uce
    0.69
    Activations Density 0.047%

    No Known Activations