© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103559
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    );
    -1.48
     use
    -1.48
    をご覧ください
    -1.42
     because
    -1.41
    in
    -1.41
     necesitar
    -1.35
     "";
    -1.35
     indicates
    -1.32
     explains
    -1.32
     is
    -1.31
    POSITIVE LOGITS
     \'
    1.63
    ###############
    1.63
    aneity
    1.56
     ۰
    1.52
     kurios
    1.51
    stalgia
    1.51
    ……"
    1.51
    
    1.46
    such
    1.45
     saa
    1.45
    Activations Density 0.020%

    No Known Activations