© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124722
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

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

    This neuron fires on capitalized algebraic‐data‐type constructors (e.g. “Some,” “Right,” “Success,” “Err,” 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
    鼍
    -2.17
    跸
    -2.06
    kurtka
    -1.90
    矬
    -1.84
    慳
    -1.83
    阄
    -1.82
    bluza
    -1.81
     Φ
    -1.80
    
    -1.80
    茕
    -1.79
    POSITIVE LOGITS
    When
    3.19
    2
    2.98
    8
    2.97
    There
    2.86
    3
    2.75
    Because
    2.72
    As
    2.70
    4
    2.67
    Since
    2.67
    One
    2.67
    Activations Density 0.001%

    No Known Activations