© 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. 929
    Prev
    Next
    INDEX
    Explanations

    over + descriptors

    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
     przeprowad
    0.80
     vergessen
    0.73
     godiš
    0.73
    어
    0.73
     entspricht
    0.73
    েও
    0.73
     eröff
    0.70
     fand
    0.69
    
    0.68
     üzerinde
    0.68
    POSITIVE LOGITS
    whelming
    1.73
    whel
    1.64
    lapping
    1.43
    indul
    1.42
    tones
    1.38
    estimating
    1.37
    subscribed
    1.33
    abundance
    1.31
    reacted
    1.30
    emphas
    1.30
    Activations Density 0.408%

    No Known Activations