© 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. 211987
    Prev
    Next
    INDEX
    Explanations

    whether X or Y

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

    in exploring

    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
     publik
    0.54
     SMAD
    0.51
    잌
    0.50
     Baat
    0.50
     delimit
    0.49
     yaad
    0.46
     Aap
    0.46
     Taal
    0.45
     samud
    0.45
     baar
    0.44
    POSITIVE LOGITS
    g
    0.52
    ا
    0.51
    gé
    0.47
    uns
    0.46
    isement
    0.46
     বজায়
    0.46
     ঘণ্টায়
    0.45
    érature
    0.44
    lès
    0.44
    efeu
    0.43
    Activations Density 0.000%

    No Known Activations