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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 2018
    Prev
    Next
    INDEX
    Explanations

    place names and foreign word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_65k_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
     Y
    0.35
    !
    0.35
      
    0.34
    /
    0.33
     custom
    0.33
    ↵↵
    0.32
     H
    0.32
    (
    0.32
     x
    0.32
     k
    0.31
    POSITIVE LOGITS
    atório
    0.58
    ICAGO
    0.55
    atória
    0.52
    avasena
    0.52
    ínsula
    0.52
    ității
    0.51
    iería
    0.51
    ASHINGTON
    0.51
    ména
    0.51
    OSED
    0.50
    Activations Density 5.462%

    No Known Activations