© 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. 161066
    Prev
    Next
    INDEX
    Explanations

    patient populations and clinical trials

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

    Active Learning and financial terms

    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
    ामुळे
    0.50
     ナ
    0.49
    hitung
    0.49
     १९
    0.48
    טו
    0.48
     タ
    0.47
             
    0.46
    terminal
    0.46
    s
    0.46
    pré
    0.46
    POSITIVE LOGITS
     repositories
    0.60
     খানকে
    0.55
     Munster
    0.48
     prematurely
    0.48
     placing
    0.48
     dismay
    0.47
     replies
    0.46
     decidido
    0.46
    演员
    0.46
     arrays
    0.46
    Activations Density 0.000%

    No Known Activations