© 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. 63414
    Prev
    Next
    INDEX
    Explanations

    Albert Hall concert

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

    knows outcomes or strategy game

    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
     ASTM
    0.57
     SDR
    0.52
     SBT
    0.52
     $
    0.51
     IAU
    0.49
    quate
    0.49
     STD
    0.48
    hands
    0.48
    সর্ব
    0.48
     ellipsoid
    0.48
    POSITIVE LOGITS
    ing
    0.49
    ('+
    0.48
    ای
    0.44
    ിച്ചി
    0.42
    impinan
    0.42
    ционного
    0.41
     ตำ
    0.41
    ब्बे
    0.41
    óis
    0.41
    outputPath
    0.41
    Activations Density 0.000%

    No Known Activations