© 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. 887
    Prev
    Next
    INDEX
    Explanations

    Google AI and ecosystem

    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
    ấc
    0.59
    
    0.59
    oplane
    0.59
    abdomen
    0.57
    &-
    0.57
    eterm
    0.56
    leetcode
    0.55
    iformis
    0.55
    wicket
    0.54
    POSITIVE LOGITS
    ®
    1.63
    ®,
    1.48
    ®.
    1.47
    Ⓡ
    1.45
     Originals
    1.37
     ®
    1.35
     Presents
    1.22
     Studios
    1.18
    ™
    1.16
     Labs
    1.13
    Activations Density 1.439%

    No Known Activations