© 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. 182270
    Prev
    Next
    INDEX
    Explanations

    particular, meaningful, international, extended, safely

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

    controls camera

    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
    𝒸
    0.48
     abril
    0.47
     precarious
    0.47
    anomaly
    0.46
     subtiliter
    0.46
     AFFAIRS
    0.46
    pleasant
    0.45
    quem
    0.45
     dès
    0.44
     fie
    0.44
    POSITIVE LOGITS
     Substitute
    0.50
    Drive
    0.48
    Download
    0.46
    GroupId
    0.45
     Download
    0.44
    黨
    0.44
     Starter
    0.44
     Malaria
    0.43
     Karate
    0.43
     Khim
    0.43
    Activations Density 0.001%

    No Known Activations