© 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. 7406
    Prev
    Next
    INDEX
    Explanations

    financial figures and years

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

    Base64 encoding

    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
    ↵
    0.21
    Ã
    0.18
    æ
    0.18
    begin
    0.18
     the
    0.17
    0.17
    ;
    0.17
    [
    0.17
      
    0.17
    ã
    0.17
    POSITIVE LOGITS
     ভোক্তার
    0.23
     onboarding
    0.23
     rulemaking
    0.22
     omnichannel
    0.19
    โยชน์
    0.19
     estoppel
    0.19
     injunctive
    0.18
     সম্পূর্ণরূপে
    0.18
    เพื่อให้
    0.18
    嫄
    0.18
    Activations Density 0.009%

    No Known Activations