© 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. 78377
    Prev
    Next
    INDEX
    Explanations

    welcome to, verify whether

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

    Google Search Console, Analytics

    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
    odesmium
    0.50
    ્રી
    0.47
    ré
    0.47
    जलवायु
    0.46
    Ӣ
    0.46
    نی
    0.45
    收购
    0.45
     سینٹی
    0.44
    发布
    0.44
    ऊंगी
    0.44
    POSITIVE LOGITS
     subTest
    0.45
     Expt
    0.43
     gauss
    0.42
    綽
    0.40
     unregistered
    0.39
     expt
    0.39
     iff
    0.39
     bap
    0.38
     overt
    0.38
    fty
    0.38
    Activations Density 0.001%

    No Known Activations