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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16039
    Prev
    Next
    INDEX
    Explanations

    insurance coverage

    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
     informée
    0.54
    📅
    0.50
    cèle
    0.50
     nghiên
    0.49
     साजरा
    0.48
     высокие
    0.48
    意识到
    0.48
     লিখিতে
    0.48
     финанси
    0.46
    etapkan
    0.46
    POSITIVE LOGITS
    ,
    0.48
    6
    0.47
    、
    0.47
     and
    0.47
     coolness
    0.45
    ،
    0.45
     attribut
    0.43
    または
    0.42
    4
    0.42
    2
    0.42
    Activations Density 0.001%

    No Known Activations