© 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. 73618
    Prev
    Next
    INDEX
    Explanations

    Intents and Android Activity

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

    This neuron activates on code‐style tokens—especially programming identifiers, class/type names, constants, and API method or field 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
     kupić
    -1.32
     in
    -1.30
    terse
    -1.29
    鯔
    -1.29
    :
    -1.27
     powiedzieć
    -1.23
     praktis
    -1.20
     verschiedenen
    -1.20
     romantis
    -1.20
     temen
    -1.20
    POSITIVE LOGITS
     but
    1.77
    でしたが
    1.50
    arised
    1.40
    𝑿
    1.37
    豳
    1.34
    inį
    1.32
    taglio
    1.30
    ⟳
    1.26
    ächlich
    1.25
    fillment
    1.25
    Activations Density 0.002%

    No Known Activations