© 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. 40441
    Prev
    Next
    INDEX
    Explanations

    Agn prefixes: agnostic, Agnese, Agnis, Agnarsson, agent, Agememnon

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

    This neuron is triggered by the three-letter sequence “agn” (as in Agnieszka, Agnese, agnostic, 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
    ar
    -3.70
    る
    -3.23
    瑧
    -2.73
    our
    -2.66
    k
    -2.61
    猻
    -2.52
    )$
    -2.50
    𝐞
    -2.50
    珢
    -2.42
    了的
    -2.41
    POSITIVE LOGITS
    "
    2.50
    凩
    2.44
    ቕ
    2.41
     And
    2.38
     هنگام
    2.33
     нова
    2.30
    </em>
    2.27
     africain
    2.25
    晦
    2.20
    驁
    2.17
    Activations Density 0.002%

    No Known Activations