© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128543
    Prev
    Next
    INDEX
    Explanations

    fuse box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arden
    0.51
    ibo
    0.50
    ő
    0.49
    abb
    0.47
    सि
    0.47
    an
    0.46
    utas
    0.46
    oda
    0.45
     organik
    0.44
    講的是
    0.44
    POSITIVE LOGITS
     inflater
    0.49
    ネルギー
    0.47
     lesquelles
    0.43
    ﻳ
    0.43
    ColorLegend
    0.43
     to
    0.42
    辍
    0.42
     Faites
    0.42
    MJX
    0.42
     †
    0.42
    Activations Density 0.000%

    No Known Activations