© 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. 63308
    Prev
    Next
    INDEX
    Explanations

    stability constants and theorems

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

    quadratic formulas and algebra

    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
     algebraic
    0.45
    EMPTY
    0.44
     ನೆಲ
    0.43
     কতক
    0.42
    တစ်
    0.41
     SCHOOL
    0.41
     алге
    0.41
    oggler
    0.41
    $\--
    0.40
     establecido
    0.40
    POSITIVE LOGITS
     critically
    0.39
     suicide
    0.39
     dépasse
    0.39
     Hé
    0.39
    痊
    0.39
     stress
    0.37
     horrors
    0.36
    щают
    0.36
    იდან
    0.36
     heals
    0.36
    Activations Density 0.000%

    No Known Activations