© 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. 127561
    Prev
    Next
    INDEX
    Explanations

    Share your, Page, services, largest, Fudge way, soon update

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

    narrative techniques, or fear had

    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
     ભે
    0.49
    鬍
    0.40
     تشوف
    0.40
     الداله
    0.40
     किराये
    0.40
     ధర
    0.40
     هز
    0.39
    Ü
    0.39
     pobreza
    0.39
     daño
    0.39
    POSITIVE LOGITS
    🖥
    0.42
     jednak
    0.42
     Прав
    0.42
     однако
    0.40
     reborn
    0.40
    ằ
    0.40
     ngọt
    0.39
     deoarece
    0.39
    и
    0.39
     guarantee
    0.39
    Activations Density 0.001%

    No Known Activations