© 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. 129322
    Prev
    Next
    INDEX
    Explanations

    legal citations or specific items

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

    legal consultant attorney employee

    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
    ộng
    0.46
     напол
    0.43
    最大
    0.43
    льних
    0.42
    рые
    0.42
    üll
    0.41
    
    0.41
    зы
    0.40
    ອດ
    0.39
     реак
    0.39
    POSITIVE LOGITS
     unaware
    0.47
    法人
    0.46
     lacking
    0.45
    6
    0.45
     consultant
    0.44
     eliminated
    0.44
     employee
    0.44
     entitlement
    0.44
     halts
    0.43
     consulting
    0.43
    Activations Density 0.001%

    No Known Activations