© 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. 73193
    Prev
    Next
    INDEX
    Explanations

    URLs, email addresses, scientific citations

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

    The neuron is picking up reference-style markers (e.g. the “[” or “(” that begin citation labels like “[1]” or “(2)”) and similar short technical tokens used in scholarly citations.

    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
     '
    -2.27
     spezi
    -2.14
    灕
    -2.06
     speziellen
    -1.97
     beinahe
    -1.95
     zusätz
    -1.95
    They
    -1.90
     Fazit
    -1.88
    Those
    -1.86
    Even
    -1.78
    POSITIVE LOGITS
    泐
    2.56
    镚
    2.39
    ꪹ
    2.33
    lgari
    2.20
    ᠊
    2.17
     you
    2.17
    },
    2.16
    ሖ
    2.16
    哙
    2.14
    籥
    2.14
    Activations Density 0.001%

    No Known Activations