© 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. 67807
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     for
    -4.19
     with
    -3.83
     after
    -3.66
     as
    -3.56
     or
    -3.53
     at
    -3.48
     in
    -3.45
     when
    -3.44
     while
    -3.34
     until
    -3.27
    POSITIVE LOGITS
     !!!!
    3.08
     ludicrous
    3.08
     ridiculously
    3.08
    蛲
    3.05
     insanely
    3.03
     唯美
    3.03
     REALLY
    3.03
    粜
    2.98
     !!!!!
    2.97
     delightfully
    2.97
    Activations Density 0.005%

    No Known Activations