© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85416
    Prev
    Next
    INDEX
    Explanations

    python library calls

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

    This neuron fires on occurrences of common Python library aliases (e.g. “np” for NumPy and “pd” for pandas).

    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
    ztes
    -2.44
     esfuer
    -2.22
    thodoxy
    -2.14
     katk
    -2.13
    quelize
    -2.06
     aktiviteter
    -2.05
    </>
    -2.05
    thodox
    -2.05
    fordshire
    -2.02
     öppna
    -2.02
    POSITIVE LOGITS
    .
    2.84
    {
    2.19
     What
    2.11
     It
    2.09
    Getting
    2.08
    --
    2.05
    <b>
    2.03
    '
    2.03
     Because
    2.00
    <
    2.00
    Activations Density 0.002%

    No Known Activations