© 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. 30787
    Prev
    Next
    INDEX
    Explanations

    grant, videos, leave, task, page

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

    SwiftUI body property

    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
     bowel
    0.28
     myśl
    0.28
     nghỉ
    0.28
    醣
    0.28
     bệnh
    0.28
     σύμφωνα
    0.27
     গর্
    0.27
     bañ
    0.27
     bột
    0.26
     डेयरी
    0.26
    POSITIVE LOGITS
    that
    0.28
     Another
    0.25
     О
    0.25
     That
    0.24
    That
    0.24
     that
    0.24
    annotation
    0.24
    ટ
    0.24
    ための
    0.23
    }'
    0.23
    Activations Density 0.000%

    No Known Activations