© 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. 113421
    Prev
    Next
    INDEX
    Explanations

    words used in defining conditions

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

    km and miles

    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
    cols
    0.46
    ಧಿಕ
    0.46
    avista
    0.45
    getVersion
    0.43
    >(</
    0.43
     amministrat
    0.43
    iyam
    0.42
     થ
    0.42
     objs
    0.42
    tons
    0.42
    POSITIVE LOGITS
    OSU
    0.45
     देखील
    0.43
     Epis
    0.43
     الشعر
    0.43
     ጥላ
    0.43
     অপহরণকারীদের
    0.42
     समर्
    0.41
    色列
    0.41
     ستر
    0.40
     شاهد
    0.40
    Activations Density 0.001%

    No Known Activations