Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169245
    Prev
    Next
    INDEX
    Explanations

    late 20th-century manufacture and robotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     КАК
    0.52
    Как
    0.50
     megfelelő
    0.47
    Wie
    0.47
    লেট
    0.46
    Як
    0.46
    ivalent
    0.44
    😺
    0.44
     टाइप्स
    0.44
    Optimal
    0.43
    POSITIVE LOGITS
     dpi
    0.44
     Akira
    0.43
     годы
    0.41
    所
    0.40
     years
    0.40
    原
    0.40
    oa
    0.40
    ,
    0.40
     tarifs
    0.39
    tif
    0.38
    Activations Density 0.004%

    No Known Activations