© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2550
    Prev
    Next
    INDEX
    Explanations

    rides and thrills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கண
    0.73
     readable
    0.71
     Cookbook
    0.71
     இலக்கிய
    0.70
     fennel
    0.70
    Notebook
    0.69
     नोटबुक
    0.69
    贤
    0.69
     தமி
    0.67
    كتب
    0.67
    POSITIVE LOGITS
     thrill
    1.81
     rides
    1.76
     thrills
    1.70
     adrenaline
    1.66
     rollercoaster
    1.66
    🎢
    1.61
     Rides
    1.58
     ride
    1.57
     amusement
    1.53
     waterslide
    1.50
    Activations Density 0.739%

    No Known Activations