© 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. 106236
    Prev
    Next
    INDEX
    Explanations

    and, pretreatment, myths, rooms

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

    Tagging and categorization

    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
     квартире
    0.51
    让人
    0.46
     владель
    0.46
    麻烦
    0.46
     Fiverr
    0.44
    蚝
    0.44
    ъек
    0.43
    WhiteBalance
    0.42
     Bản
    0.42
     воспользоваться
    0.42
    POSITIVE LOGITS
     anden
    0.54
     AND
    0.53
     and
    0.51
     thiab
    0.50
     ಮತ್ತು
    0.49
     आणि
    0.47
    और
    0.46
    Ж
    0.46
     andre
    0.46
    tests
    0.45
    Activations Density 0.001%

    No Known Activations