© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2687
    Prev
    Next
    INDEX
    Explanations

    line, master, dating, bullet, urban

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

    The neuron selectively fires on named‐entity tokens—especially proper names of organizations, places, farms, companies, universities, and other specific institutions.

    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
    .
    1.02
    !
    0.85
    o
    0.83
    /
    0.82
    '
    0.80
    $.
    0.79
    am
    0.79
    ie
    0.78
    lik
    0.77
     admon
    0.77
    POSITIVE LOGITS
     Nowadays
    1.05
    Nowadays
    0.96
     touristic
    0.94
     différents
    0.91
     compagnies
    0.91
     لهذه
    0.91
     europeos
    0.90
     hauptsächlich
    0.90
     nowadays
    0.89
     Firstly
    0.89
    Activations Density 0.133%

    No Known Activations