© 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. 256812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    descricao
    0.48
     forskj
    0.48
    pyrazine
    0.48
    भीर
    0.48
     tempHeader
    0.47
    ཧ
    0.46
    temperatur
    0.46
    reflectionMap
    0.45
    ዎች
    0.45
    yemek
    0.45
    POSITIVE LOGITS
     activists
    0.47
     Alberta
    0.47
     activist
    0.47
     leaders
    0.46
    /
    0.46
     Edmonton
    0.45
     bloc
    0.45
     army
    0.44
     MLAs
    0.44
     influenz
    0.44
    Activations Density 0.001%

    No Known Activations