© 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. 205885
    Prev
    Next
    INDEX
    Explanations

    verb action and formation

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

    mixture of languages

    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
    1
    0.78
    4
    0.58
    5
    0.55
    are
    0.53
    for
    0.53
     ﺍﻟ
    0.52
    8
    0.51
    0
    0.50
    )^{*}
    0.49
    x
    0.49
    POSITIVE LOGITS
     싶은
    0.54
    ました
    0.54
    ského
    0.53
    ছি
    0.51
    싶
    0.51
    ంది
    0.50
    る
    0.48
    いました
    0.47
    かったです
    0.46
     ముందుకు
    0.45
    Activations Density 0.008%

    No Known Activations