© 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. 34-GEMMASCOPE-RES-131K
    7. 60455
    Prev
    Next
    INDEX
    Explanations

    location or java packages

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

    This neuron activates on fully qualified code package or import declarations (e.g. long dotted Java package 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_34/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
    karz
    -0.78
    vault
    -0.75
    глу
    -0.74
    usammen
    -0.74
    unki
    -0.73
    шар
    -0.73
    acken
    -0.72
    تو
    -0.72
    Rat
    -0.71
    getExternal
    -0.71
    POSITIVE LOGITS
     Location
    1.28
    Location
    1.20
     location
    1.13
     locations
    0.98
     Locations
    0.96
     LOCATION
    0.92
     lokasi
    0.83
     Cub
    0.83
     living
    0.82
    ocation
    0.82
    Activations Density 0.009%

    No Known Activations