© 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. 182898
    Prev
    Next
    INDEX
    Explanations

    customer designs and imports

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

    universes, developing, fat, plan, observing

    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
     ملف
    0.48
     basın
    0.48
     중에
    0.48
     각각
    0.46
    ı
    0.46
    s
    0.45
     פ
    0.45
     जब
    0.45
    al
    0.43
    lov
    0.43
    POSITIVE LOGITS
     উদ্বাস্তুদের
    0.53
     уеннары
    0.46
    BLACKLIST
    0.46
    সম্মত
    0.46
     Jeux
    0.45
     Enough
    0.44
    Games
    0.44
    খ্যান
    0.44
     полноцен
    0.43
     GameOver
    0.43
    Activations Density 0.001%

    No Known Activations