© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71662
    Prev
    Next
    INDEX
    Explanations

    tokens following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     healthful
    0.48
     maximized
    0.44
    豁
    0.43
     intercal
    0.43
     prematurely
    0.42
     jeopardize
    0.42
     premature
    0.41
     hampers
    0.41
     compressible
    0.40
     dlatego
    0.40
    POSITIVE LOGITS
    era
    0.50
    ng
    0.48
    et
    0.47
    rie
    0.46
    eric
    0.43
     जुनून
    0.43
     dejan
    0.42
    <0xAB>
    0.42
    що
    0.42
    ڭ
    0.42
    Activations Density 0.003%

    No Known Activations