© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3807
    Prev
    Next
    INDEX
    Explanations

    adventure sports and games

    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_29_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
    ższej
    0.64
    hwnd
    0.64
    IPv
    0.64
    liono
    0.60
    ulières
    0.59
    ਘ
    0.58
    लेंट
    0.58
    ffler
    0.58
    ගත
    0.58
    🔮
    0.58
    POSITIVE LOGITS
     sports
    4.77
     athletic
    4.48
     sport
    4.39
     Sports
    4.32
     athletes
    4.30
    Sports
    4.30
     Sport
    4.12
     athlete
    4.09
     athletics
    4.07
    sports
    4.03
    Activations Density 0.439%

    No Known Activations