© 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. 260036
    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
     מח
    0.54
     мм
    0.49
    desIP
    0.48
     sostenible
    0.47
     ребен
    0.46
     manualmente
    0.46
     כש
    0.46
     ש
    0.46
     Dato
    0.46
     estre
    0.45
    POSITIVE LOGITS
    atha
    0.50
    yd
    0.49
    ively
    0.47
    aining
    0.46
    acyj
    0.46
    일까지
    0.46
    ioneer
    0.46
    А
    0.46
    utils
    0.46
    昶
    0.46
    Activations Density 0.001%

    No Known Activations