© 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. 7394
    Prev
    Next
    INDEX
    Explanations

    suggesting outdoor activities

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

    The neuron detects words that express personal preferences, hobbies, or things someone enjoys.

    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
     माहौल
    0.54
    Quartz
    0.54
    startup
    0.53
    encour
    0.53
    Ấ
    0.53
    grunt
    0.53
    ತು
    0.53
    虏
    0.53
     bless
    0.52
    न्नी
    0.52
    POSITIVE LOGITS
     skiing
    1.60
     shopping
    1.56
     bowling
    1.54
     golfing
    1.49
     boating
    1.41
     swimming
    1.38
    Shopping
    1.38
     Shopping
    1.38
    游泳
    1.37
    shopping
    1.36
    Activations Density 0.656%

    No Known Activations