© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47481
    Prev
    Next
    INDEX
    Explanations

    order, forward, spare, staple, remove

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Mejor
    0.47
     Quality
    0.42
     Pepper
    0.42
     starfish
    0.40
     variété
    0.40
     ड
    0.39
     QUALITY
    0.39
     আমরা
    0.38
     COME
    0.38
     qualidade
    0.38
    POSITIVE LOGITS
    Their
    0.43
    their
    0.43
    क्योंकि
    0.42
    ulia
    0.41
    because
    0.40
    ണ്ടാ
    0.39
     তাঁদের
    0.38
     તેમની
    0.38
    >`;
    0.38
    Outlet
    0.38
    Activations Density 0.001%

    No Known Activations