© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11236
    Prev
    Next
    INDEX
    Explanations

    Guide to

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

    This neuron spotlights the word “Guide” when it appears (especially as part of titles or headings).

    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_24_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
    ان
    0.78
    anov
    0.78
     createWindow
    0.71
    镤
    0.71
     motionProxy
    0.70
    นาย
    0.69
    dioxide
    0.69
    μα
    0.68
    ның
    0.68
    ベイ
    0.67
    POSITIVE LOGITS
     Guide
    0.75
     throwback
    0.72
     Victorian
    0.72
     Corps
    0.71
     GUIDE
    0.71
     Weekly
    0.70
    ,
    0.70
     averaging
    0.70
     Which
    0.68
     Son
    0.67
    Activations Density 0.001%

    No Known Activations