© 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-65K
    7. 44880
    Prev
    Next
    INDEX
    Explanations

    bt documentation

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     out
    0.50
    )!
    0.49
     solicitar
    0.47
    pping
    0.46
     rinse
    0.46
     relieve
    0.45
     eggplant
    0.45
     добавить
    0.45
    VPN
    0.44
     〢
    0.44
    POSITIVE LOGITS
     Pensions
    0.60
    ляются
    0.45
    ↵↵
    0.43
    История
    0.43
    许多
    0.42
     Energia
    0.41
     miejscowości
    0.41
    certain
    0.40
     Katherine
    0.40
    acciones
    0.40
    Activations Density 0.002%

    No Known Activations