© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 167860
    Prev
    Next
    INDEX
    Explanations

    pounds of ice

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

    files or information

    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
    Negative Logits
    ﻠ
    0.49
     নানা
    0.48
     যাই
    0.45
    БО
    0.45
    OTOS
    0.45
     задания
    0.45
    OTS
    0.44
    BILL
    0.44
     участия
    0.44
    ุ
    0.44
    POSITIVE LOGITS
    യാണ്
    0.47
     Paige
    0.47
     hebt
    0.45
    amini
    0.44
     burdensome
    0.44
     anten
    0.42
     يمكنك
    0.42
    有问题
    0.42
     recue
    0.41
    esen
    0.41
    Activations Density 0.001%

    No Known Activations