© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41666
    Prev
    Next
    INDEX
    Explanations

    geographical places and biological classifications

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

    North American geographic names, particularly places like Cumberland and references to taxonomic classifications in Hymenoptera (wasp/bee order).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects capitalized proper nouns (e.g., geographic place names and taxonomic genus names).

    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
    </strong>
    -2.91
    」，
    -2.75
    躂
    -2.48
    {
    -2.47
    </i>
    -2.45
    </h1>
    -2.41
    んや
    -2.33
    """
    -2.23
    </u>
    -2.22
    );
    -2.20
    POSITIVE LOGITS
    “
    3.11
    ]
    2.58
    $
    2.48
    ments
    2.38
    on
    2.36
    鹇
    2.30
     этого
    2.27
     were
    2.27
    k
    2.19
    褙
    2.19
    Activations Density 0.011%

    No Known Activations