© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13828
    Prev
    Next
    INDEX
    Explanations

    digits, decimals, place value

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

    numbers and digit 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
    Not in Any Lists

    No Comments

    Negative Logits
     Lagoon
    0.52
     Allergy
    0.51
     Gabriela
    0.49
     parques
    0.49
     ساح
    0.48
    StarService
    0.48
     کشت
    0.48
    缇
    0.47
     zarządz
    0.47
     çat
    0.47
    POSITIVE LOGITS
     digits
    1.25
    digits
    1.18
    Digits
    1.08
     decimal
    1.06
     digit
    1.02
     DECIMAL
    0.95
    decimal
    0.91
    digit
    0.88
    addDigit
    0.87
     decimals
    0.86
    Activations Density 0.011%

    No Known Activations