© 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. 235782
    Prev
    Next
    INDEX
    Explanations

    international legal and emotional connection

    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
    Not in Any Lists

    No Comments

    Negative Logits
    most
    0.53
    ه
    0.52
    purge
    0.51
    Court
    0.49
    replacement
    0.49
     Daytona
    0.47
    प्रकारे
    0.47
    a
    0.46
     Alic
    0.46
    paw
    0.46
    POSITIVE LOGITS
     estimular
    0.53
     emozioni
    0.50
     amores
    0.49
     sentimientos
    0.49
     viennent
    0.48
     emociones
    0.48
     symptômes
    0.48
     বিপর্য
    0.47
     sintomi
    0.47
     conjunta
    0.47
    Activations Density 0.001%

    No Known Activations