© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130947
    Prev
    Next
    INDEX
    Explanations

    courts, judges, litigation

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

    opposing viewpoints and beliefs

    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
    Photograph
    0.50
    入
    0.48
    Communication
    0.48
    Photography
    0.46
    意義
    0.46
    コミュニケーション
    0.46
    Https
    0.46
    物流
    0.45
    Publish
    0.45
    灼
    0.45
    POSITIVE LOGITS
     jueces
    0.48
    courts
    0.47
     ignores
    0.47
     courts
    0.47
     crystall
    0.46
    enemy
    0.45
    ammo
    0.45
     endGame
    0.45
     сн
    0.45
    ignore
    0.44
    Activations Density 0.001%

    No Known Activations