© 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. 58679
    Prev
    Next
    INDEX
    Explanations

    play an instrumental role

    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
    красивые
    -1.59
    ꜆
    -1.55
    ～～
    -1.52
    When
    -1.49
     saludables
    -1.48
     persönlich
    -1.47
     ``
    -1.47
    ``
    -1.45
     grundsätzlich
    -1.45
     gewiß
    -1.44
    POSITIVE LOGITS
    f
    1.78
     \
    1.62
    k
    1.59
     통해
    1.54
     whom
    1.54
    j
    1.53
     сможет
    1.52
    re
    1.50
    \
    1.50
    ubakar
    1.46
    Activations Density 0.026%

    No Known Activations