© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48445
    Prev
    Next
    INDEX
    Explanations

    achievements and developments

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

    The neuron is detecting formal, bureaucratic or corporate/government announcement language—that is, institutional or official-style vocabulary.

    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
    Either
    -1.69
    Those
    -1.69
    either
    -1.66
     either
    -1.62
    最初
    -1.57
    These
    -1.56
    新しい
    -1.55
    When
    -1.54
    這些
    -1.53
    Some
    -1.52
    POSITIVE LOGITS
     which
    2.08
     this
    1.95
     also
    1.71
     its
    1.70
    なければならない
    1.59
    舔
    1.56
     again
    1.54
    typer
    1.54
    の人に
    1.52
     logistical
    1.49
    Activations Density 0.079%

    No Known Activations