© 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. 66502
    Prev
    Next
    INDEX
    Explanations

    code, UI, and neurobiology terms

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

    The neuron flags domain‐specific proper nouns—especially CamelCase API/class names or specialized scientific terms.

    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
    re
    -2.81
    When
    -2.48
    The
    -2.47
    And
    -2.41
    ка
    -2.34
    目前的
    -2.30
    ud
    -2.28
    To
    -2.28
    Why
    -2.23
    Regardless
    -2.23
    POSITIVE LOGITS
     Inhalte
    2.22
     legislación
    2.20
     Our
    2.14
     reminding
    2.14
    蔸
    2.13
    .}
    2.11
     alcuni
    2.08
     semelh
    2.06
     Schwangerschaft
    2.05
     raça
    2.03
    Activations Density 0.002%

    No Known Activations