© 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. 74064
    Prev
    Next
    INDEX
    Explanations

    phrases after specific words

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

    The neuron activates on technical or domain‐specific keywords—particularly names of commands, parameters, features, or operations in software/documentation contexts.

    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
     personalización
    -1.93
    茈
    -1.88
     כמה
    -1.81
     gastronomía
    -1.80
     kinda
    -1.77
     пыта
    -1.77
     tos
    -1.76
     effectuer
    -1.75
    ​​​
    -1.70
     iluminación
    -1.70
    POSITIVE LOGITS
     at
    2.59
     When
    2.25
     while
    2.23
     There
    2.20
     for
    2.11
     Although
    2.06
     While
    2.03
     with
    1.99
     on
    1.98
     Initially
    1.98
    Activations Density 0.182%

    No Known Activations