© 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. 65310
    Prev
    Next
    INDEX
    Explanations

    . strategy | In | may | better | from | your | Pakistan | gentle | marine

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

    each line, preparation, globalization

    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
     एशियाई
    0.48
    但是在
    0.45
    natures
    0.45
     लेकिन
    0.44
    wrong
    0.44
     एप्पल
    0.43
    mortar
    0.43
    p
    0.43
     Changing
    0.43
     Wrong
    0.43
    POSITIVE LOGITS
    .
    0.55
     dulce
    0.49
     trycatch
    0.47
    σαν
    0.47
     westward
    0.46
    一体
    0.45
     utilize
    0.45
     can
    0.44
     referentes
    0.44
     fest
    0.43
    Activations Density 0.000%

    No Known Activations