© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    countries and locations

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

    metadata analysis

    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
    原来的
    0.58
    ４
    0.49
    唐
    0.47
    老师
    0.47
    关键词
    0.47
    ină
    0.45
    кол
    0.45
     원래
    0.45
    
    0.45
    大众
    0.44
    POSITIVE LOGITS
     hva
    0.50
     samtidig
    0.50
     hvad
    0.47
    alysis
    0.47
     g
    0.46
     μη
    0.46
    fähigkeit
    0.46
     є
    0.45
    ostomy
    0.45
    fähig
    0.45
    Activations Density 0.000%

    No Known Activations