© 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. 59121
    Prev
    Next
    INDEX
    Explanations

    very + descriptive word

    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
     then
    -2.33
    叆
    -2.02
    鼍
    -1.92
     &
    -1.90
    ࿊
    -1.87
    鈇
    -1.75
    periods
    -1.74
     ngan
    -1.71
    認真
    -1.70
     allerlei
    -1.66
    POSITIVE LOGITS
    Those
    2.83
    Despite
    2.47
     Those
    2.47
    Although
    2.44
    There
    2.39
    However
    2.31
    While
    2.30
    Some
    2.11
     είχε
    2.06
     There
    2.03
    Activations Density 0.007%

    No Known Activations