© 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. 70758
    Prev
    Next
    INDEX
    Explanations

    foreign numbers and symbols

    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_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
    codings
    -0.97
    …
    -0.93
    genus
    -0.91
     …
    -0.90
     atuais
    -0.88
     recentes
    -0.88
    )})
    -0.84
    +%
    -0.84
    cola
    -0.82
     chronology
    -0.81
    POSITIVE LOGITS
    ︐
    0.96
    uyla
    0.91
    freundlich
    0.91
     ДЕ
    0.88
    Warto
    0.87
    máquina
    0.87
    tarta
    0.87
    🕗
    0.86
     değiş
    0.85
    ｄ
    0.85
    Activations Density 0.070%

    No Known Activations