© 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. 17522
    Prev
    Next
    INDEX
    Explanations

    expected action or outcome

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

    simulate and tested

    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
    לי
    0.52
     עבור
    0.50
    🫣
    0.50
     עם
    0.48
    િંગ
    0.47
    ቮ
    0.47
     до
    0.46
     ако
    0.46
    सरकार
    0.46
    TikTok
    0.46
    POSITIVE LOGITS
     Preface
    0.57
    ’
    0.52
     Computed
    0.50
     Computer
    0.48
       
    0.46
     Clinic
    0.45
         
    0.45
     Health
    0.45
     clinics
    0.45
     Mill
    0.45
    Activations Density 0.000%

    No Known Activations