© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 47
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     _
    0.59
     framework
    0.56
     security
    0.54
     screening
    0.54
     ending
    0.52
     cogn
    0.52
     described
    0.52
     setting
    0.50
     ‪
    0.50
     **
    0.49
    POSITIVE LOGITS
    Powered
    0.68
    Subscribe
    0.62
    Loading
    0.62
    Tweet
    0.59
    <h6>
    0.58
    Categories
    0.58
    <h5>
    0.58
    Advertisement
    0.57
    Seite
    0.57
    Mga
    0.57
    Activations Density 0.091%

    No Known Activations