© 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. 65643
    Prev
    Next
    INDEX
    Explanations

    celebrates, reviews, beautiful things

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

    betweenness centrality, discovered, coach, expensive

    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
     desolate
    0.49
     výstav
    0.46
    processable
    0.45
    линд
    0.45
     വേദ
    0.44
     довго
    0.44
    ':[
    0.44
    वनि
    0.44
     disorganized
    0.43
     raggi
    0.43
    POSITIVE LOGITS
     যেমন
    0.50
    ug
    0.49
    hc
    0.47
    hig
    0.47
    ار
    0.46
    i
    0.44
     hippocampus
    0.43
    ال
    0.42
     مناطق
    0.42
     Becoming
    0.42
    Activations Density 0.001%

    No Known Activations