© 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. 38834
    Prev
    Next
    INDEX
    Explanations

    prevent bacterial growth

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

    famous names and personalities

    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
    یدم
    0.45
    )}{\
    0.45
    indazol
    0.44
    ښ
    0.44
    izzato
    0.43
     निचले
    0.43
    scriptstyle
    0.42
    argeon
    0.41
    ộ
    0.41
    ющее
    0.41
    POSITIVE LOGITS
    Ivan
    0.47
    Brian
    0.44
    Peter
    0.44
     carbons
    0.42
    William
    0.42
     unknown
    0.42
    John
    0.42
    Elon
    0.42
     Антон
    0.42
     cucumbers
    0.41
    Activations Density 0.000%

    No Known Activations