© 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. 134613
    Prev
    Next
    INDEX
    Explanations

    violence, tension, game, code, contacts

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

    information, research, and effects

    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
     piacere
    0.49
     σημαν
    0.48
    ُمْ
    0.47
    enderung
    0.46
     เดียว
    0.46
    त्य
    0.45
    䏌
    0.44
     เงิน
    0.44
     みたい
    0.44
     書い
    0.42
    POSITIVE LOGITS
    ار
    0.55
    мм
    0.48
    数は
    0.47
    id
    0.47
     Eski
    0.47
    Ė
    0.46
    kiem
    0.46
    ar
    0.45
     Zahl
    0.45
    imų
    0.45
    Activations Density 0.000%

    No Known Activations