© 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. 144434
    Prev
    Next
    INDEX
    Explanations

    loading and unloading

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

    supported statements and theories

    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
     rejoicing
    0.44
     Kevin
    0.44
     P
    0.43
     Jonah
    0.43
     Joey
    0.43
     Joel
    0.43
     contending
    0.43
     Great
    0.42
     clar
    0.42
     Joe
    0.42
    POSITIVE LOGITS
    })$
    0.55
     honti
    0.51
     வகையில்
    0.50
     इंतजाम
    0.49
     업체
    0.49
    amı
    0.48
     있었습니다
    0.47
    ana
    0.46
    unzione
    0.46
     información
    0.46
    Activations Density 0.001%

    No Known Activations