© 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. 25694
    Prev
    Next
    INDEX
    Explanations

    Pute, lute, ante, Mante, vite

    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
    ne
    -0.92
    new
    -0.89
    night
    -0.85
    name
    -0.82
    ny
    -0.81
     infrequent
    -0.80
    nd
    -0.78
    re
    -0.78
     halting
    -0.78
    ret
    -0.77
    POSITIVE LOGITS
    aux
    0.86
    писи
    0.82
     придется
    0.81
    šech
    0.79
     Pute
    0.76
    Хотя
    0.75
     Cartes
    0.73
     laguna
    0.73
    有钱
    0.73
     Fantasia
    0.72
    Activations Density 0.104%

    No Known Activations