© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 1473
    Prev
    Next
    INDEX
    Explanations

    code execution commands

    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
     Logout
    0.59
     ANOVA
    0.58
     Delete
    0.57
     pruning
    0.51
     CRUD
    0.50
    <unused742>
    0.49
     middlewares
    0.49
     Postgres
    0.49
     チェック
    0.49
     pruned
    0.48
    POSITIVE LOGITS
    declare
    0.57
    require
    0.52
    #!/
    0.45
    import
    0.43
    asp
    0.42
    function
    0.42
     доли
    0.40
    java
    0.40
    include
    0.39
    describe
    0.39
    Activations Density 0.085%

    No Known Activations