© 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. 183281
    Prev
    Next
    INDEX
    Explanations

    promotions such as

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

    core part, statement, or line

    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
     effectuées
    0.64
     jednego
    0.53
     samego
    0.51
     údaje
    0.51
     GoName
    0.50
    ഒ
    0.49
     wła
    0.49
     Tatha
    0.49
     odgov
    0.47
    ธุ
    0.47
    POSITIVE LOGITS
    0.59
    t
    0.57
    -
    0.57
     C
    0.54
    m
    0.47
    mber
    0.46
     Test
    0.46
     G
    0.45
     (
    0.45
    ure
    0.43
    Activations Density 0.000%

    No Known Activations