© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1783
    Prev
    Next
    INDEX
    Explanations

    ```pythonmetadata```

    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_9_width_16k_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
    м
    1.83
    as
    1.49
    ি
    1.38
    ers
    1.33
    ো
    1.32
    ırd
    1.30
    ও
    1.29
    ം
    1.23
    ின்
    1.22
    te
    1.22
    POSITIVE LOGITS
     ​​
    1.05
     tranh
    1.00
    quiera
    0.98
    linewidth
    0.96
    addies
    0.95
    lst
    0.93
    buscar
    0.93
    eram
    0.92
    시키는
    0.90
     ​​​​
    0.90
    Activations Density 0.303%

    No Known Activations