© 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
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2529
    Prev
    Next
    INDEX
    Explanations

    nodejs javascript

    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
     मॉड
    0.62
    ؤول
    0.61
    orne
    0.61
    turns
    0.60
    莫
    0.59
    ASCII
    0.59
    ovar
    0.58
    turn
    0.58
    Raleway
    0.57
    WARD
    0.57
    POSITIVE LOGITS
     Bridge
    0.60
     cas
    0.60
     Breach
    0.60
     கந்த
    0.59
     canon
    0.59
     Bridges
    0.59
     bridges
    0.57
    橋
    0.55
     samos
    0.55
     Brokers
    0.55
    Activations Density 0.159%

    No Known Activations