© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    birth and death dates

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

    dates and locations

    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
     ২০২০
    0.55
     ২০২৩
    0.51
     সাম্প্রতিক
    0.49
     ২০২১
    0.48
     ২০২২
    0.48
     새
    0.45
     ২০১৯
    0.45
    새
    0.44
     trouverez
    0.44
     cuyas
    0.43
    POSITIVE LOGITS
    Death
    0.55
     death
    0.54
    death
    0.52
     damals
    0.52
     смерти
    0.51
     рождения
    0.50
    所在地
    0.50
     умер
    0.49
    fecha
    0.49
    したのは
    0.48
    Activations Density 0.021%

    No Known Activations