© 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. 84475
    Prev
    Next
    INDEX
    Explanations

    military, police, and service operations

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

    dynamic processes and states

    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
    買い物
    0.37
     चॉकलेट
    0.34
    笥
    0.33
     algéb
    0.32
    ोर
    0.32
     वित्तीय
    0.32
     civilians
    0.31
     ক্ষয়ক্ষতি
    0.31
     malzeme
    0.31
    科技
    0.30
    POSITIVE LOGITS
     AudioManager
    0.40
     Dynamical
    0.36
     Clinical
    0.35
     militares
    0.35
     Dynamic
    0.35
    ↵
    0.34
     Police
    0.34
     military
    0.34
     Live
    0.34
     Military
    0.34
    Activations Density 0.667%

    No Known Activations