© 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. 52819
    Prev
    Next
    INDEX
    Explanations

    handling gently

    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
     Galer
    0.46
     Upt
    0.44
     Nuovo
    0.44
     capa
    0.42
    нора
    0.42
     Май
    0.40
    有意
    0.40
    존
    0.39
     ইনডাক
    0.39
    cari
    0.38
    POSITIVE LOGITS
     air
    0.45
    साम
    0.41
    rimp
    0.40
    वण
    0.40
    ܚ
    0.40
     woodland
    0.40
     church
    0.40
    🇱
    0.39
     ordinance
    0.39
     firewood
    0.39
    Activations Density 0.017%

    No Known Activations