© 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. 74128
    Prev
    Next
    INDEX
    Explanations

    prime256v1 ecdsa

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

    This neuron detects occurrences of the token “cn,” typically appearing as a country code or part of import/module paths.

    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
     Also
    -2.30
    sprzed
    -2.25
    ѹ
    -2.13
    鐿
    -2.06
     lasciato
    -2.03
    Polska
    -2.00
    劻
    -1.98
     Также
    -1.97
     nuevos
    -1.92
    enido
    -1.91
    POSITIVE LOGITS
    t
    2.64
    т
    2.53
    th
    2.48
    in
    2.22
    s
    2.19
     were
    2.16
    who
    2.03
    ва
    1.98
     The
    1.96
    "
    1.95
    Activations Density 0.007%

    No Known Activations