© 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. 178629
    Prev
    Next
    INDEX
    Explanations

    Sherlock Holmes, Deep Seating, buying badges

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

    multiple NICs

    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
     harrowing
    0.44
    entire
    0.44
     foll
    0.44
     poter
    0.43
     तिवारी
    0.42
     lacer
    0.41
    壩
    0.41
     berupa
    0.41
     När
    0.41
     Bisa
    0.41
    POSITIVE LOGITS
     кноп
    0.47
    ታ
    0.45
    좆
    0.43
    ინი
    0.43
     několik
    0.43
     кнопки
    0.42
     studs
    0.42
     közül
    0.42
     звезды
    0.42
    ቡ
    0.41
    Activations Density 0.000%

    No Known Activations