© 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. 76362
    Prev
    Next
    INDEX
    Explanations

    switch wiring

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

    leaks and 0

    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
     由于
    0.48
    ennzeichnet
    0.47
     biện
    0.46
     住
    0.46
    ંકી
    0.46
    rov
    0.45
    ្ខ
    0.45
     我们
    0.45
     Bởi
    0.45
    ника
    0.44
    POSITIVE LOGITS
    0
    0.52
     quatern
    0.49
     pelas
    0.48
    ﻏ
    0.47
    ۰
    0.46
     França
    0.45
     लीक
    0.45
    Ꮼ
    0.44
     eigen
    0.44
    まさ
    0.44
    Activations Density 0.000%

    No Known Activations