© 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. 92251
    Prev
    Next
    INDEX
    Explanations

    Category, directions, currency, gallery

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

    how to understand

    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
    実に
    0.50
    म
    0.47
    нді
    0.47
     faid
    0.46
    Ṛ
    0.45
    מים
    0.43
     कहने
    0.43
     difícil
    0.43
    日が
    0.42
    കളിൽ
    0.42
    POSITIVE LOGITS
     playroom
    0.53
    getValue
    0.46
     магази
    0.46
    ctu
    0.46
    NETWORK
    0.46
    妓
    0.45
    WithMessage
    0.45
     illustrate
    0.45
    urez
    0.44
    gallery
    0.44
    Activations Density 0.001%

    No Known Activations