© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    Paris and gateway in code or protest contexts

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

    The neuron is essentially tracking how far into a long chunk of text it is and fires most strongly on tokens that occur late in extended passages.

    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
     Rehabilit
    0.78
    тых
    0.72
    treme
    0.71
     Kommunikation
    0.70
    วี
    0.70
    վ
    0.67
    ەد
    0.66
     eigentlich
    0.66
    นั้น
    0.65
    นาน
    0.64
    POSITIVE LOGITS
    )-(
    0.75
     ';'
    0.68
    eff
    0.66
    '')
    0.65
     уча
    0.64
     rendent
    0.64
     dall
    0.64
    StringUtils
    0.63
    header
    0.63
     carta
    0.62
    Activations Density 0.000%

    No Known Activations