© 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. 71429
    Prev
    Next
    INDEX
    Explanations

    soaring and flying upward

    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
    玧
    -2.41
     ͡°
    -2.27
    噚
    -2.22
     lär
    -2.16
    Etimología
    -2.16
    閙
    -2.14
    ℣
    -2.14
    ꦫ
    -2.14
    ֿ
    -2.14
    狆
    -2.14
    POSITIVE LOGITS
    )
    3.23
    ’
    3.19
    s
    3.00
    ."
    2.55
    x
    2.52
    e
    2.39
    有
    2.28
    '[
    2.27
    h
    2.27
    ,
    2.22
    Activations Density 0.001%

    No Known Activations