© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    mathematical derivative

    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
    or
    -3.38
    (
    -3.05
    </b>
    -2.80
    at
    -2.77
     или
    -2.75
    t
    -2.69
     '
    -2.67
     The
    -2.58
    \
    -2.56
    ak
    -2.55
    POSITIVE LOGITS
    酲
    4.28
    姈
    3.31
    箆
    3.09
    辚
    3.09
    ⽌
    3.00
    杙
    2.94
     manteniendo
    2.92
    铙
    2.88
    椟
    2.86
     беже
    2.84
    Activations Density 0.007%

    No Known Activations