© 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. 185226
    Prev
    Next
    INDEX
    Explanations

    time zones and deadlines

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

    development, urethra, loan, LM

    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
    Negative Logits
    AVA
    0.48
    市立
    0.45
    citizens
    0.45
    artista
    0.45
    alle
    0.44
    []}
    0.44
    delta
    0.44
    );}
    0.44
     dific
    0.44
     السياسي
    0.43
    POSITIVE LOGITS
     Millie
    0.48
     प्लांट्स
    0.46
     Кі
    0.45
     προϊ
    0.45
    uit
    0.44
     Mila
    0.44
     δε
    0.42
     amort
    0.42
     συγκεκρι
    0.42
     Password
    0.41
    Activations Density 0.000%

    No Known Activations