© 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. 651
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on tokens that occur very late in a long sequence—that is, on words appearing near the end of the document.

    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
    льным
    0.84
    ushroom
    0.83
    <0x8D>
    0.82
    лит
    0.82
    льную
    0.79
    podcast
    0.77
    ꩡ
    0.77
    ಠ
    0.76
     Brewery
    0.75
    дных
    0.74
    POSITIVE LOGITS
     здійс
    0.75
     keltiradi
    0.68
    กรณี
    0.66
     arrondies
    0.65
     dàng
    0.64
     impass
    0.64
    comers
    0.64
     dove
    0.62
     décrites
    0.62
     descrizione
    0.62
    Activations Density 0.000%

    No Known Activations