© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7269
    Prev
    Next
    INDEX
    Explanations

    large numbers and quantities

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

    millions and billions

    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
     IncludeField
    0.23
    pInBuffer
    0.22
     మొక్క
    0.22
     আহত
    0.22
    伡
    0.22
     Chirurgien
    0.22
     پیشن
    0.21
    糁
    0.21
    䀖
    0.21
    愎
    0.21
    POSITIVE LOGITS
     million
    0.36
    -
    0.35
    8
    0.34
    0
    0.34
    _
    0.34
    5
    0.33
    %
    0.32
     billion
    0.31
    K
    0.31
     thousand
    0.30
    Activations Density 1.068%

    No Known Activations