© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    reference manual or section

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

    The neuron activates on occurrences of the word “reference” (e.g. in headings, URLs, or section titles).

    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
     вашем
    -1.73
     включая
    -1.73
    ꪹ
    -1.70
     bekämp
    -1.66
     ибо
    -1.66
    your
    -1.63
    ꔹ
    -1.58
     are
    -1.57
     verur
    -1.56
    enablog
    -1.55
    POSITIVE LOGITS
     Référence
    2.06
    ‪.‬‬
    1.78
     prius
    1.77
     and
    1.77
    洐
    1.74
     milano
    1.68
    鄚
    1.68
    AUSTRALIA
    1.67
    ierungen
    1.63
    graphiques
    1.63
    Activations Density 0.064%

    No Known Activations