© 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. 74854
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables

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

    The neuron detects inline references to numbered figures and tables (e.g., “Figure 1,” “Table 3”).

    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
     to
    -2.77
     which
    -2.63
     or
    -2.41
     for
    -2.25
     It
    -2.22
     should
    -2.06
     who
    -2.06
     where
    -2.05
     that
    -2.03
     whose
    -2.03
    POSITIVE LOGITS
    鸩
    1.74
     ´
    1.73
     grandiose
    1.72
     impec
    1.70
     無地
    1.70
     effici
    1.65
     borboleta
    1.65
    鐽
    1.60
    legte
    1.59
     visites
    1.59
    Activations Density 0.011%

    No Known Activations