© 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. 13099
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects the token “more,” as used in “read more” or “… more” continuation prompts.

    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
     美国
    0.61
    ﻤ
    0.60
     黃
    0.59
    РИ
    0.58
     Courtesy
    0.57
     Crafted
    0.57
    vette
    0.57
    ش
    0.57
    嗘
    0.57
     国家
    0.56
    POSITIVE LOGITS
     batal
    0.54
     bort
    0.52
     betek
    0.51
     semua
    0.51
     mij
    0.51
     jong
    0.50
     fabrik
    0.50
     na
    0.49
     infusions
    0.49
     seu
    0.49
    Activations Density 0.000%

    No Known Activations