© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75227
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and functions

    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
     When
    -3.20
     If
    -3.08
    Surprisingly
    -2.97
    0
    -2.91
     or
    -2.69
    When
    -2.61
     Which
    -2.61
    There
    -2.61
    3
    -2.59
    One
    -2.58
    POSITIVE LOGITS
    狁
    2.89
    榦
    2.69
    瓛
    2.50
    ا
    2.45
    a
    2.44
     illustre
    2.30
    籥
    2.27
    箧
    2.19
     aident
    2.17
     feront
    2.17
    Activations Density 0.001%

    No Known Activations