© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3633
    Prev
    Next
    INDEX
    Explanations

    looking to solve

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ä
    0.50
     behaviors
    0.49
     Similarly
    0.49
    ipsych
    0.46
    opausal
    0.46
    ath
    0.45
    in
    0.45
    spers
    0.45
     Their
    0.45
     behaviours
    0.44
    POSITIVE LOGITS
    )]),
    0.51
    ﺪ
    0.51
     înce
    0.51
     причиной
    0.50
     亻
    0.49
     раствор
    0.49
    ചന
    0.48
     பிரச்சினை
    0.48
     Конгрегация
    0.48
     වන
    0.48
    Activations Density 0.000%

    No Known Activations