© 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. 129691
    Prev
    Next
    INDEX
    Explanations

    have on or and

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

    marketing and generation guidance

    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
     محکمہ
    0.50
    𒆤
    0.49
    
    0.46
     खुले
    0.45
    ского
    0.44
    мос
    0.44
     сотрудни
    0.43
    有意
    0.43
    अब
    0.43
     परिस्थिति
    0.42
    POSITIVE LOGITS
     jazz
    0.55
    oa
    0.52
     primates
    0.50
    h
    0.49
     one
    0.48
     Marseille
    0.48
    ol
    0.48
     pal
    0.48
     mau
    0.48
     TBA
    0.48
    Activations Density 0.000%

    No Known Activations