© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41031
    Prev
    Next
    INDEX
    Explanations

    member of a group

    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
     of
    -1.84
    ],
    -1.58
    訛
    -1.48
    ↵↵
    -1.45
    .,
    -1.41
    oucí
    -1.41
    сколько
    -1.38
     always
    -1.38
     "'
    -1.35
     "[
    -1.34
    POSITIVE LOGITS
     değildir
    1.65
    お楽しみに
    1.65
     проекти
    1.63
    雰囲
    1.62
    Cuando
    1.55
     спокойно
    1.52
    こんなに
    1.52
     riguarda
    1.49
    Quando
    1.48
    Considering
    1.47
    Activations Density 0.034%

    No Known Activations