© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74597
    Prev
    Next
    INDEX
    Explanations

    currents relief yellow flight effort rings attracts

    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
    Negative Logits
    㧿
    0.47
    嘏
    0.45
    掝
    0.45
    सबसे
    0.45
    廾
    0.44
    зде
    0.44
    ઉન
    0.44
    嘊
    0.44
     submarines
    0.43
    顗
    0.43
    POSITIVE LOGITS
    cloth
    0.41
     Vic
    0.41
    visual
    0.41
    photo
    0.40
    ocot
    0.40
    call
    0.38
     patrol
    0.38
    indexed
    0.38
     retrato
    0.37
    checkpoint
    0.36
    Activations Density 0.001%

    No Known Activations