© 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. 58881
    Prev
    Next
    INDEX
    Explanations

    Xcode code and imports

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

    The neuron fires on uppercase configuration keys and identifiers (e.g. BUILD_DIR, FRAMEWORK_SEARCH_PATHS) in project or build‐system files.

    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
     are
    -1.30
     ‘’
    -1.22
    braio
    -1.21
     ''
    -1.16
    拶
    -1.16
     samt
    -1.13
     sausage
    -1.12
     sowie
    -1.12
     شما
    -1.11
     liksom
    -1.10
    POSITIVE LOGITS
     trattano
    1.28
    iPhone
    1.22
     PATRICK
    1.13
    品です
    1.13
     campesinos
    1.13
     PACIFIC
    1.08
     Filtration
    1.07
     POLLUTION
    1.07
     only
    1.05
     Comprar
    1.05
    Activations Density 0.720%

    No Known Activations