© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    words starting with He

    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
    じた
    0.45
    igenza
    0.42
    形の
    0.40
     ಕಾನೂ
    0.39
    ಿಸಿದ
    0.38
    셈
    0.38
    낀
    0.37
    落ち
    0.37
    uhnya
    0.37
    ulları
    0.37
    POSITIVE LOGITS
     ヘ
    0.62
     хе
    0.60
     heap
    0.57
     heats
    0.57
     HE
    0.54
     heuristic
    0.52
    Hem
    0.52
     헤
    0.52
     ஹீ
    0.52
    HE
    0.51
    Activations Density 0.098%

    No Known Activations