© 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. 216015
    Prev
    Next
    INDEX
    Explanations

    born in 19

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

    introverted, niche, chemicals

    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
     Validación
    0.46
     வழக்கு
    0.45
     Änderung
    0.43
     अलर्ट
    0.42
    xhr
    0.42
    лесо
    0.41
    检验
    0.41
     શું
    0.40
    ියාව
    0.40
    ඒ
    0.40
    POSITIVE LOGITS
     into
    0.51
    h
    0.50
     ambient
    0.46
    c
    0.46
     assembly
    0.45
     ори
    0.43
    ORIENT
    0.43
     c
    0.43
     integrals
    0.42
     হ
    0.42
    Activations Density 0.001%

    No Known Activations