© 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. 138543
    Prev
    Next
    INDEX
    Explanations

    Russian agency, ongoing activities

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

    learners, defense, world, how

    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
     maid
    0.52
     patric
    0.50
    ↵↵
    0.48
    ate
    0.48
     best
    0.48
     Frage
    0.48
     apothe
    0.47
     festival
    0.47
     K
    0.47
     trainer
    0.46
    POSITIVE LOGITS
    美国的
    0.48
    ວນ
    0.47
    وانات
    0.46
    
    0.45
    水印
    0.45
    地铁
    0.44
    俟
    0.43
    ભાગ
    0.43
    股
    0.42
    鍦
    0.41
    Activations Density 0.000%

    No Known Activations