© 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. 65346
    Prev
    Next
    INDEX
    Explanations

    signals or sigils

    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
    并在
    -2.69
    ing
    -2.45
    쨩
    -2.31
    話の
    -2.27
     he
    -2.17
     of
    -2.14
    t
    -2.13
     with
    -2.09
     owing
    -2.06
    consola
    -2.02
    POSITIVE LOGITS
    ൎ
    2.59
     ที่
    2.59
     rampant
    2.55
    e
    2.48
     captiv
    2.45
    瓩
    2.41
     erase
    2.31
     Eigentü
    2.30
    Actually
    2.28
     intrigues
    2.28
    Activations Density 0.003%

    No Known Activations