© 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. 10-GEMMASCOPE-RES-131K
    7. 19913
    Prev
    Next
    INDEX
    Explanations

    item after item

    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_10/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
    s
    -1.83
     all
    -1.52
     Their
    -1.48
    U
    -1.41
    but
    -1.41
     and
    -1.41
     recibiendo
    -1.40
    可爱的
    -1.35
     three
    -1.32
    even
    -1.32
    POSITIVE LOGITS
     *
    1.41
    %\]
    1.39
     maría
    1.39
    Trọng
    1.35
    Làm
    1.33
     a
    1.33
     inconvénients
    1.32
     atividade
    1.31
     moreno
    1.31
     peines
    1.30
    Activations Density 0.017%

    No Known Activations