© 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. 100840
    Prev
    Next
    INDEX
    Explanations

    decided, affirmed, ordered, held

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

    The neuron selectively activates on headings and metadata labels in legal opinions (e.g. “Argued:”, “Decided:”, “Present,” dates, colons).

    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
     we
    -1.58
     I
    -1.45
    enablog
    -1.39
     its
    -1.38
     \
    -1.38
     you
    -1.35
     démarrer
    -1.34
     наша
    -1.30
    憷
    -1.28
    錼
    -1.28
    POSITIVE LOGITS
    There
    1.59
     londres
    1.55
     for
    1.49
    :
    1.45
     in
    1.43
    Some
    1.41
    ♪♪
    1.30
    的看着
    1.26
     Considered
    1.25
    ;)
    1.23
    Activations Density 0.062%

    No Known Activations