© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75505
    Prev
    Next
    INDEX
    Explanations

    warrant that

    np_acts-logits-general · gemini-2.5-flash-lite

    personal prestige and true motives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     рі
    0.49
     TRACK
    0.48
     நடந்து
    0.46
     مسیر
    0.45
     hospitalized
    0.45
     회사
    0.44
     ビ
    0.44
     طلب
    0.44
     WINTER
    0.44
     美術
    0.43
    POSITIVE LOGITS
     dexterity
    0.52
    जर
    0.50
    म्यान
    0.48
     agility
    0.48
    ډ
    0.48
    undo
    0.47
    铢
    0.46
    دام
    0.46
    دس
    0.46
    సో
    0.46
    Activations Density 0.001%

    No Known Activations