© 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. 45434
    Prev
    Next
    INDEX
    Explanations

    foreign language

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

    basic greetings and operations, Fibonacci sum

    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
    0
    0.53
     voters
    0.53
     new
    0.52
     gamers
    0.52
     np
    0.50
     workers
    0.50
     Games
    0.50
     latest
    0.50
    (
    0.50
    9
    0.50
    POSITIVE LOGITS
    艳
    0.59
    Más
    0.58
    妆
    0.54
    材质
    0.53
    лығы
    0.52
     роско
    0.52
    公园
    0.52
    Despatx
    0.51
    棂
    0.50
     листья
    0.50
    Activations Density 0.000%

    No Known Activations