© 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. 34-GEMMASCOPE-RES-131K
    7. 91443
    Prev
    Next
    INDEX
    Explanations

    organizations and professional contexts

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

    The neuron fires strongly on proper nouns denoting organizations or institutions (e.g. NIH, Oracle, British Academy, Facebook).

    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
     by
    -3.23
    由
    -1.35
     توسط
    -1.31
     снова
    -1.09
    ByID
    -1.04
     Manufact
    -0.98
     provided
    -0.98
     وسی
    -0.97
     aquellos
    -0.96
    ところは
    -0.96
    POSITIVE LOGITS
     to
    1.89
     who
    1.60
     in
    1.29
     during
    1.25
     towards
    1.24
     after
    1.21
    )))))
    1.20
    themselves
    1.20
    เพื่อ
    1.19
    during
    1.18
    Activations Density 0.222%

    No Known Activations