© 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. 225071
    Prev
    Next
    INDEX
    Explanations

    specific features of webpages

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

    lists, bullet points, and explanations

    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
    টি
    0.50
    ्रेडिट
    0.47
     letteratura
    0.46
    İZ
    0.45
    ᅩ
    0.44
    👃
    0.44
     aliran
    0.44
    Ⲣ
    0.44
    KEL
    0.44
    𝗟
    0.44
    POSITIVE LOGITS
    et
    0.53
    is
    0.49
    ade
    0.46
    y
    0.46
     unwarrant
    0.46
    issait
    0.46
    emption
    0.44
    arr
    0.44
    anov
    0.43
    워
    0.43
    Activations Density 0.001%

    No Known Activations