© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7663
    Prev
    Next
    INDEX
    Explanations

    invention relates to

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

    This neuron detects specialized identifiers or technical terms—especially capitalized or mixed-case class, method, library, or patent-section 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
    1
    -2.45
    $
    -2.19
     
    -2.14
    6
    -2.03
    2
    -1.92
    P
    -1.88
     \
    -1.82
     $
    -1.81
    3
    -1.81
     one
    -1.78
    POSITIVE LOGITS
    :✨
    2.33
     イラストレーション
    2.16
    ॄ
    2.03
    `
    1.97
    鿬
    1.95
     rente
    1.91
     })
    1.88
     CreateTagHelper
    1.88
     手绘
    1.88
    cimientos
    1.87
    Activations Density 0.004%

    No Known Activations