© 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. 67893
    Prev
    Next
    INDEX
    Explanations

    but however contrast

    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
    同様に
    -1.37
    );
    -1.36
     its
    -1.33
     to
    -1.23
     просто
    -1.23
     simply
    -1.22
              
    -1.17
     especially
    -1.15
    低い
    -1.13
     on
    -1.12
    POSITIVE LOGITS
     però
    2.42
     jedoch
    1.93
     allerdings
    1.80
     caveat
    1.72
     اما
    1.71
     however
    1.71
    但
    1.70
    Однако
    1.65
    但是
    1.54
     kuitenkin
    1.54
    Activations Density 0.087%

    No Known Activations