© 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. 233407
    Prev
    Next
    INDEX
    Explanations

    foreign language content

    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
     cerevisiae
    0.43
     ανθρώ
    0.42
    恙
    0.41
     biomarkers
    0.41
     CHEMISTRY
    0.40
    λέ
    0.40
     mathsize
    0.40
     সুস্থ
    0.39
     Thrones
    0.39
     curvatures
    0.39
    POSITIVE LOGITS
    ലീസ്
    0.46
     السيارة
    0.46
    bieter
    0.44
     Nahr
    0.44
    ಾರಂಭ
    0.43
    砓
    0.43
    परेशन
    0.43
     автомобиль
    0.42
     ನಗರ
    0.42
    DialogOpen
    0.42
    Activations Density 0.001%

    No Known Activations