© 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. 11189
    Prev
    Next
    INDEX
    Explanations

    UVP

    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
     by
    -2.28
     with
    -2.27
     an
    -2.25
     three
    -2.09
     and
    -2.09
     it
    -2.06
     through
    -1.98
     after
    -1.90
     before
    -1.86
     as
    -1.80
    POSITIVE LOGITS
    (!__
    2.13
    vantaged
    1.81
     BEING
    1.75
     当
    1.75
    This
    1.69
    RUnlock
    1.68
     många
    1.66
     renk
    1.66
    adaş
    1.66
    この
    1.65
    Activations Density 0.002%

    No Known Activations