© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19210
    Prev
    Next
    INDEX
    Explanations

    prevent five common diseases

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

    various languages and concepts

    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
    under
    0.53
    ussen
    0.50
    ala
    0.48
    下
    0.47
    ता
    0.47
    stung
    0.47
    sa
    0.47
    P
    0.47
    р
    0.47
    ny
    0.46
    POSITIVE LOGITS
     gelişmeler
    0.61
     fuese
    0.55
     ሂደት
    0.55
     கூறியுள்ளார்
    0.54
     கொண்டுள்ளது
    0.54
     espè
    0.53
     veille
    0.52
     çalışmaları
    0.52
     angiogenesis
    0.52
     bột
    0.51
    Activations Density 0.000%

    No Known Activations