© 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. 212863
    Prev
    Next
    INDEX
    Explanations

    supplier manufacturer

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

    individual performing, patron, obtain, combat, early life, initial testing

    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
    ydat
    0.49
    ER
    0.49
    BDF
    0.45
    :
    0.44
    యర్
    0.44
     presumptive
    0.44
    🥕
    0.43
     lemongrass
    0.43
     ndi
    0.43
    uate
    0.43
    POSITIVE LOGITS
    星
    0.52
    months
    0.47
     الاخر
    0.47
     رأ
    0.47
     সক্রিয়
    0.47
    实际上
    0.44
     चलाना
    0.44
    垄
    0.44
     Ελλάδα
    0.43
    喝酒
    0.43
    Activations Density 0.002%

    No Known Activations