© 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. 54926
    Prev
    Next
    INDEX
    Explanations

    channels and support

    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
    yp
    0.50
    ό
    0.46
    sun
    0.45
    aria
    0.45
     класса
    0.44
    eres
    0.44
    osa
    0.43
    ኞ
    0.43
     incumbents
    0.42
    nsen
    0.42
    POSITIVE LOGITS
    帏
    0.52
     हमे
    0.49
     oops
    0.45
     pier
    0.45
     materialistic
    0.45
     dock
    0.44
     hotel
    0.43
     corollary
    0.43
     materi
    0.43
     potrebné
    0.43
    Activations Density 0.005%

    No Known Activations