© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38660
    Prev
    Next
    INDEX
    Explanations

    National Center for

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

    names of national organizations, institutes, centers, or commissions.

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

    The neuron activates on tokens that are part of formal institution or agency names (e.g. “National Center…,” “National Council…,” “National Register…,” 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_34/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
    aleb
    -0.88
     MACHINE
    -0.88
     tjen
    -0.84
     ganador
    -0.83
    公告
    -0.83
     Terkait
    -0.81
     fantastique
    -0.81
     bleach
    -0.81
     personaje
    -0.80
     Nouveau
    -0.80
    POSITIVE LOGITS
     part
    0.75
     происходит
    0.73
     based
    0.71
     summarized
    0.70
     presenza
    0.70
     Create
    0.69
     improving
    0.69
     including
    0.68
     name
    0.68
     anticipo
    0.68
    Activations Density 0.024%

    No Known Activations