© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2298
    Prev
    Next
    INDEX
    Explanations

    math operators and numbers

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

    mentions of concrete, specific entities such as people, roles, organizations, places, and notable events

    oai_token-act-pair · gpt-5Triggered by @smilgaveronika
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    возмо
    1.35
    ạo
    1.24
    是一些
    1.17
    ශ්‍ය
    1.11
     bữa
    1.09
     قوه
    1.08
     以及
    1.07
    ු
    1.07
    צו
    1.07
    trong
    1.06
    POSITIVE LOGITS
     nearest
    2.00
     closest
    1.92
    nearest
    1.85
    closest
    1.79
     farthest
    1.73
     furthest
    1.63
     coolest
    1.59
     principale
    1.45
     oldest
    1.44
     loudest
    1.44
    Activations Density 0.656%

    No Known Activations