© 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. 31470
    Prev
    Next
    INDEX
    Explanations

    countries and locations

    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
     psychic
    0.36
     time
    0.35
    时间
    0.34
    时间和
    0.34
    ){
    0.34
     autod
    0.33
    Controller
    0.33
    period
    0.33
    )</
    0.32
    smoothed
    0.32
    POSITIVE LOGITS
     vše
    0.42
     Lévy
    0.40
    依然
    0.38
    inité
    0.38
     vectorize
    0.37
     liberate
    0.36
    ës
    0.36
     টাক
    0.36
     modernas
    0.36
    Ĥ
    0.36
    Activations Density 0.001%

    No Known Activations