© 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. 43572
    Prev
    Next
    INDEX
    Explanations

    code attributes and declarations

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

    The neuron fires on code identifiers ending with “Attribute,” i.e. .NET attribute class 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
    }
    -2.67
     staunch
    -2.47
     blissful
    -2.28
     seductive
    -2.23
    what
    -2.20
     riveting
    -2.13
     poignant
    -2.11
     prized
    -2.09
    ꔹ
    -2.08
     .....
    -2.05
    POSITIVE LOGITS
     of
    2.64
    卺
    2.25
     ボーダー
    2.25
     itinéraires
    2.16
     بالإضافة
    2.13
     praticamente
    2.08
     “
    2.08
    0
    2.06
    ↵
    2.05
    ぽん
    2.03
    Activations Density 0.000%

    No Known Activations