© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63168
    Prev
    Next
    INDEX
    Explanations

    python scikit-learn and machine learning

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

    The neuron fires on tokens that are part of machine‐learning or data‐science library names (e.g. “scikit,” “learn,” “sklearn,” “numpy,” “pandas,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    derr
    -0.60
     хле
    -0.60
     тесто
    -0.59
     ont
    -0.59
     theater
    -0.59
     Chir
    -0.59
     μετά
    -0.58
    avaj
    -0.58
    SIM
    -0.58
    pul
    -0.58
    POSITIVE LOGITS
     sklearn
    1.83
     ml
    1.21
    Ml
    1.15
     caret
    1.13
     ML
    1.13
    sci
    1.10
     MACHINE
    1.10
     Ml
    1.10
    sk
    1.09
    caret
    1.06
    Activations Density 0.069%

    No Known Activations