© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80721
    Prev
    Next
    INDEX
    Explanations

    programming libraries and proper nouns

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

    The neuron activates on names of external libraries, frameworks, or tooling packages (e.g. imported module or annotation identifiers).

    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
     you
    -2.55
    衚
    -2.41
     стоковая
    -2.28
    觧
    -2.22
     allarg
    -2.22
     ujar
    -2.17
    自然的
    -2.17
    遹
    -2.11
     akrab
    -2.11
     attivo
    -2.08
    POSITIVE LOGITS
    </h2>
    2.75
     -
    2.20
    [
    2.11
    –
    2.02
    \
    1.94
    ");
    1.93
    ’
    1.84
    \\
    1.82
     những
    1.82
    blurRadius
    1.81
    Activations Density 0.002%

    No Known Activations