© 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. 102338
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite

    expressions involving subtraction operations, particularly in mathematical formulas and variable assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -1.79
     créations
    -1.48
    aterdag
    -1.36
    anstalt
    -1.33
     következő
    -1.30
     icônes
    -1.29
     goûts
    -1.28
     számára
    -1.27
    prits
    -1.27
     planètes
    -1.27
    POSITIVE LOGITS
     we
    1.53
     one
    1.47
     the
    1.45
     anymore
    1.42
     its
    1.41
     nor
    1.40
    直至
    1.34
     unless
    1.34
     altogether
    1.32
     until
    1.29
    Activations Density 0.141%

    No Known Activations