© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73608
    Prev
    Next
    INDEX
    Explanations

    San Juan and similar place names

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

    The neuron activates on Spanish‐style place names prefixed by “San,” e.g. “San Juan,” “San Pedro,” “San Luis,” etc.

    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
    {
    -2.08
     znale
    -1.98
    Mereka
    -1.96
    Hanya
    -1.92
    with
    -1.88
     Startseite
    -1.88
     afirmar
    -1.88
     Their
    -1.87
     powinna
    -1.84
     Feinde
    -1.82
    POSITIVE LOGITS
     of
    2.45
    。”
    2.09
    weightedMode
    2.02
    “
    2.00
    ”—
    1.97
     \
    1.90
    '});
    1.89
     marcato
    1.86
    "));
    1.80
    ènements
    1.78
    Activations Density 0.014%

    No Known Activations