© 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. 191493
    Prev
    Next
    INDEX
    Explanations

    commercial real, double classic, credit cards, terrestrial archives, corporate tax

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

    comedian prompts

    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
     azul
    0.51
    in
    0.46
     Ashland
    0.46
     manzana
    0.45
     गाँवों
    0.45
    小
    0.45
     temprana
    0.45
    ການ
    0.45
     Ayl
    0.44
     assin
    0.44
    POSITIVE LOGITS
    อร์
    0.48
    ரிய
    0.45
    応
    0.43
    ียม
    0.43
    рг
    0.43
    Drinks
    0.42
     diffusivity
    0.41
    Diff
    0.41
     nonzero
    0.40
    Vacancy
    0.40
    Activations Density 0.000%

    No Known Activations