© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    potential or possibility

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

    could you tell me

    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
     are
    1.02
     as
    0.91
    are
    0.89
    ার
    0.77
     savoir
    0.68
    ഡ്
    0.62
     жінок
    0.61
    ாம்
    0.60
    టీ
    0.60
    ු
    0.60
    POSITIVE LOGITS
    י
    1.10
    ي
    1.08
    i
    0.96
    ו
    0.91
    و
    0.87
    մ
    0.83
     conceivably
    0.78
    ;
    0.78
     feas
    0.76
    <0x0D>
    0.74
    Activations Density 0.164%

    No Known Activations