© 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. 74422
    Prev
    Next
    INDEX
    Explanations

    billions, partnerships, and numbers

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

    AI Agents, supervised algorithm matching

    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
     Cinema
    0.48
     inital
    0.47
     lugs
    0.47
    ۰
    0.46
    ین
    0.45
    erals
    0.43
     recesses
    0.43
     objects
    0.42
    سین
    0.42
    梟
    0.42
    POSITIVE LOGITS
     bilhões
    0.55
    rz
    0.50
     مليار
    0.50
     свят
    0.49
     забе
    0.49
    зой
    0.48
     भागीदारों
    0.48
     الصحي
    0.48
     свиде
    0.47
     млрд
    0.47
    Activations Density 0.001%

    No Known Activations