© 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. 218062
    Prev
    Next
    INDEX
    Explanations

    instructions and consequences

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

    mathematical expressions and lists

    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
     emoc
    0.47
    怡
    0.46
     subcl
    0.46
     prawdzi
    0.45
     lymphatic
    0.44
     potom
    0.43
     dė
    0.42
     भावनात्मक
    0.42
    सूस
    0.42
     эмоциона
    0.41
    POSITIVE LOGITS
    komm
    0.46
    Alaska
    0.45
    um
    0.45
    uur
    0.45
    corresponding
    0.44
    庇
    0.44
    OR
    0.43
    Compar
    0.43
     উদাহরণ
    0.43
     орби
    0.43
    Activations Density 0.001%

    No Known Activations