© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    code and command examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    0.74
     •
    0.73
    ・
    0.73
    ]-
    0.72
    |-
    0.71
    _{+}-
    0.71
    loat
    0.71
     side
    0.70
     sied
    0.69
     ・
    0.69
    POSITIVE LOGITS
    ```
    1.09
     ```
    1.01
    ```{
    0.70
    ``
    0.69
    权力
    0.69
    <code>
    0.69
    Wing
    0.67
    肌肉
    0.67
    Jewish
    0.67
    JAK
    0.66
    Activations Density 0.142%

    No Known Activations