© 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. 238658
    Prev
    Next
    INDEX
    Explanations

    proving or disproving assumptions

    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
    簪
    0.45
    وما
    0.45
    لوان
    0.44
    我说
    0.43
    и
    0.43
    家具
    0.42
    ᖏ
    0.42
    ocarcinoma
    0.42
    oplasma
    0.41
    <0xAC>
    0.41
    POSITIVE LOGITS
     athletes
    0.55
     satisfies
    0.53
     championship
    0.53
     proves
    0.53
     sports
    0.53
     playoffs
    0.53
     postseason
    0.52
    🏉
    0.52
     allows
    0.52
     šport
    0.52
    Activations Density 0.000%

    No Known Activations