© 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. 179778
    Prev
    Next
    INDEX
    Explanations

    fingerprint sensor

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

    SDXC card slot

    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
    </code>
    0.50
    ງານ
    0.47
    omsday
    0.47
     pathophys
    0.45
    Ⲡ
    0.45
    icyclic
    0.44
     growths
    0.43
    ໌
    0.43
     regiones
    0.43
    ׳
    0.43
    POSITIVE LOGITS
     نشوف
    0.45
    Tester
    0.45
     sty
    0.41
     kasa
    0.41
     الحكم
    0.41
     يطلع
    0.40
    引进
    0.40
    اسي
    0.39
     zvol
    0.39
     اسكت
    0.39
    Activations Density 0.000%

    No Known Activations