© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9477
    Prev
    Next
    INDEX
    Explanations

    camera, location, database access

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

    This neuron primarily responds to very common function words—especially high-frequency articles and prepositions like “of,” “the,” and “to.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AGT
    0.57
     Marx
    0.55
    佗
    0.55
     नितिन
    0.54
     юго
    0.54
     remote
    0.53
     Gottlieb
    0.53
     belong
    0.52
    restling
    0.52
    魂
    0.51
    POSITIVE LOGITS
     Permissions
    1.20
    Permission
    1.18
     Permission
    1.16
     permission
    1.15
     permissions
    1.15
     Camera
    1.02
    permission
    1.02
    Permissions
    1.02
     camera
    1.01
     ক্যামেরা
    1.00
    Activations Density 0.073%

    No Known Activations