© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205683
    Prev
    Next
    INDEX
    Explanations

    medical `markings`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     прикла
    0.49
     склад
    0.49
     сча
    0.48
     рит
    0.47
     불구
    0.46
     کیوں
    0.46
    ą
    0.45
    摺
    0.45
    മ്പർ
    0.45
    amaya
    0.45
    POSITIVE LOGITS
    )$
    0.50
    $
    0.45
    )$,
    0.45
    льку
    0.43
    $,
    0.42
    版的
    0.42
    )$.
    0.40
     Geographical
    0.40
     version
    0.40
     Heuer
    0.40
    Activations Density 0.002%

    No Known Activations