© 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. 68308
    Prev
    Next
    INDEX
    Explanations

    speed values

    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
     jobb
    -1.30
     todėl
    -1.28
    izoen
    -1.27
     poprzez
    -1.27
     protruding
    -1.27
    ㈠
    -1.27
     travailleurs
    -1.26
     noteworthy
    -1.26
     незавер
    -1.23
     emplois
    -1.23
    POSITIVE LOGITS
     speeds
    1.63
     speed
    1.49
     môžu
    1.34
     它
    1.34
     مرحله
    1.33
     มัน
    1.30
     majú
    1.29
     glimmer
    1.28
     ไม่
    1.27
     tenham
    1.27
    Activations Density 0.070%

    No Known Activations