© 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. 19536
    Prev
    Next
    INDEX
    Explanations

    components and their characteristics

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

    The neuron identifies specialized scientific or technical terms—long, multi‐syllable domain‐specific nouns.

    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
    鐽
    -1.77
     "..\..\..\
    -1.72
    </tfoot>
    -1.65
    pecified
    -1.59
     dAtA
    -1.57
     of
    -1.57
    providedIn
    -1.55
    鸩
    -1.55
    datable
    -1.55
    ViewById
    -1.55
    POSITIVE LOGITS
     and
    2.48
     which
    2.28
     characteristics
    1.82
     their
    1.81
     changes
    1.80
     excessively
    1.77
     especially
    1.69
     related
    1.69
     particularly
    1.66
     configuration
    1.64
    Activations Density 0.612%

    No Known Activations