© 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. 327
    Prev
    Next
    INDEX
    Explanations

    programming and SQL syntax

    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
     spermato
    1.08
    ilustración
    0.99
    judicial
    0.99
    蒾
    0.92
    AGRIC
    0.89
    molecular
    0.88
    ¹.
    0.87
    綃
    0.86
    推出了
    0.85
     monumental
    0.85
    POSITIVE LOGITS
     className
    2.02
     class
    1.93
     />
    1.79
     id
    1.75
     style
    1.70
    />
    1.69
     href
    1.67
     xmlns
    1.60
    ></
    1.57
    className
    1.57
    Activations Density 0.075%

    No Known Activations