© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85504
    Prev
    Next
    INDEX
    Explanations

    example or examples

    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
    を中心
    -1.24
     racconta
    -1.21
     desarrollan
    -1.17
     المسؤول
    -1.16
     continúas
    -1.16
     пассажи
    -1.14
     palavras
    -1.14
    なのです
    -1.13
    CharCode
    -1.13
     don
    -1.11
    POSITIVE LOGITS
     of
    1.73
    gemeester
    1.55
     but
    1.55
    ။
    1.53
     cuyos
    1.41
    呦
    1.41
    When
    1.40
     demonstrate
    1.35
    尛
    1.34
    Here
    1.34
    Activations Density 0.107%

    No Known Activations