© 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-65K
    7. 45987
    Prev
    Next
    INDEX
    Explanations

    places to visit

    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_65k_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
    $,
    0.47
    ってきた
    0.46
     vision
    0.44
     Moulton
    0.43
     severally
    0.43
    ﺎ
    0.43
    ﾞ
    0.43
    ﻱ
    0.42
     настолько
    0.41
     Ritter
    0.41
    POSITIVE LOGITS
     Okinawa
    0.51
     yık
    0.48
     Ü
    0.47
    awing
    0.44
     nõ
    0.43
    share
    0.43
     yıll
    0.43
    reason
    0.42
     ըն
    0.42
    awt
    0.42
    Activations Density 0.008%

    No Known Activations