© 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. 108618
    Prev
    Next
    INDEX
    Explanations

    international legal proceedings

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

    illegal actions and their consequences

    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
    ್
    0.46
    фр
    0.44
    י
    0.44
    奥
    0.42
    狞
    0.41
    chairman
    0.39
     insidious
    0.38
    ъ
    0.38
     oxalic
    0.38
    ฌ
    0.38
    POSITIVE LOGITS
     conductas
    0.52
     sécur
    0.51
     evaluación
    0.50
     evaluaciones
    0.50
     বিচার
    0.49
     allere
    0.48
     zunächst
    0.47
     consiguió
    0.45
     désormais
    0.44
     bezpeč
    0.44
    Activations Density 0.000%

    No Known Activations