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. 1976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    An
    0.49
    Z
    0.49
    Forest
    0.48
    Re
    0.46
    The
    0.46
    Theta
    0.46
    Bar
    0.45
    To
    0.45
    A
    0.45
    For
    0.45
    POSITIVE LOGITS
    utives
    0.60
    ities
    0.59
     happenings
    0.56
    isés
    0.55
     sellers
    0.55
    isierte
    0.54
    🕣
    0.54
     editions
    0.54
    izacin
    0.53
    ishly
    0.53
    Activations Density 5.848%

    No Known Activations