© 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-16K
    7. 11357
    Prev
    Next
    INDEX
    Explanations

    set followed by forth, up, aside, out

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

    set the stage

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    (
    0.83
    шой
    0.69
    athe
    0.64
    ного
    0.63
    нын
    0.59
    不稳定
    0.58
     shocking
    0.57
     substitutions
    0.57
     complémentaires
    0.57
    (+
    0.55
    POSITIVE LOGITS
    set
    1.09
    is
    0.99
    Set
    0.91
     セット
    0.86
     Set
    0.83
    setting
    0.82
     सेट
    0.81
    ’
    0.80
    SET
    0.79
     설정
    0.78
    Activations Density 1.502%

    No Known Activations