© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1246
    Prev
    Next
    INDEX
    Explanations

    disclaimers

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find copyright notices (the © symbol alongside dates).

    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
    ﻭ
    1.37
    hão
    1.23
    İN
    1.20
    Vý
    1.15
    ﻋ
    1.13
     POINTS
    1.12
    ణ్
    1.11
     regolare
    1.10
    อาการ
    1.09
    Př
    1.09
    POSITIVE LOGITS
    ︎
    1.30
     Engels
    1.20
     Louvre
    1.17
    ️
    1.15
     Getty
    1.13
     Copyright
    1.11
     Cem
    1.11
     Metallica
    1.11
     Chim
    1.10
     Schwarzenegger
    1.10
    Activations Density 0.008%

    No Known Activations