© 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. 221888
    Prev
    Next
    INDEX
    Explanations

    non- exclusive, non-transferable, non-assignable

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

    requiresis about

    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
    関西
    0.50
     اینکه
    0.50
    写真
    0.49
    {
    0.46
    sizes
    0.45
     Banquet
    0.45
    手に
    0.43
    acola
    0.43
     banquet
    0.43
     другой
    0.43
    POSITIVE LOGITS
    ﻲ
    0.52
    лез
    0.48
     teri
    0.47
     kali
    0.46
     אז
    0.46
     عال
    0.45
    recursive
    0.45
     menuMobile
    0.45
     terap
    0.44
    ಂದ
    0.44
    Activations Density 0.000%

    No Known Activations