© 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. 174254
    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
     लिखी
    0.49
     ур
    0.45
    茶叶
    0.45
     অন্ত
    0.44
    ρους
    0.44
    อาจ
    0.44
    솎
    0.42
    mys
    0.42
    ம்
    0.41
    北
    0.41
    POSITIVE LOGITS
     visionary
    0.42
     stringent
    0.40
     vk
    0.40
     spider
    0.40
     dynamics
    0.40
     mex
    0.40
    is
    0.39
     perawatan
    0.39
     stk
    0.39
     зи
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.