© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129881
    Prev
    Next
    INDEX
    Explanations

    keras and xerox

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized to pick up on mentions of “Keras” (including imports like `keras` or `tensorflow.keras`) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    訁
    -2.98
    
    -2.83
    凊
    -2.70
    枓
    -2.67
    瑨
    -2.59
     This
    -2.52
    菹
    -2.50
    
    -2.47
    loggedin
    -2.47
     ส์
    -2.45
    POSITIVE LOGITS
    from
    2.42
    ные
    2.22
    </b>
    2.17
    ∽
    2.14
     sabotage
    2.13
     المنزل
    2.08
    ！”
    2.06
     "/",
    2.02
     pleas
    2.02
    or
    2.02
    Activations Density 0.001%

    No Known Activations