© 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. 39894
    Prev
    Next
    INDEX
    Explanations

    fell asleep, patent infringers

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

    defining or describing entities

    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
     latitudine
    0.46
     cuando
    0.46
     beginning
    0.45
     unchanging
    0.43
     [
    0.43
     unsettled
    0.42
    ض
    0.42
    ):(
    0.41
     margine
    0.41
     afuera
    0.41
    POSITIVE LOGITS
     관련
    0.53
    Bild
    0.49
     יוד
    0.48
     пришлось
    0.47
     невероят
    0.47
    ojo
    0.45
     sə
    0.45
    प्रोड
    0.45
    ėje
    0.44
     组件
    0.44
    Activations Density 0.000%

    No Known Activations