© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92408
    Prev
    Next
    INDEX
    Explanations

    addition and subtraction connection

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

    arithmetic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sy
    0.42
    bons
    0.41
     savings
    0.40
    Expr
    0.40
     bends
    0.39
     Power
    0.39
     Precis
    0.38
     os
    0.38
    蛀
    0.38
    βα
    0.38
    POSITIVE LOGITS
    Subtract
    0.54
    subtract
    0.48
     subtracting
    0.46
     subtraction
    0.44
     Subtract
    0.44
    adding
    0.43
     subtract
    0.42
    
    0.42
    덧
    0.42
    뺄
    0.42
    Activations Density 0.023%

    No Known Activations