© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    people's names

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

    personal names and associated descriptions

    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
    သည့်
    0.33
    字节
    0.30
    鑣
    0.29
    <unused27>
    0.29
    能够
    0.29
    毫米
    0.29
    <unused19>
    0.28
    <unused79>
    0.28
    颗粒
    0.27
     nginx
    0.27
    POSITIVE LOGITS
    ara
    0.39
    ’
    0.39
    ra
    0.37
    ita
    0.36
    ia
    0.35
    io
    0.34
    ka
    0.34
    anda
    0.34
    ite
    0.34
    ika
    0.34
    Activations Density 0.276%

    No Known Activations