© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    The neuron flags the very first meaningful word of a new text segment—that is, it activates on paragraph or section‐start tokens.

    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
    ar
    0.93
    šky
    0.82
    掾
    0.82
     desist
    0.82
     dicht
    0.80
    ate
    0.79
     sợ
    0.79
    ﻟ
    0.79
    em
    0.77
     del
    0.77
    POSITIVE LOGITS
    IZING
    0.83
     capacités
    0.81
     PARTS
    0.77
    ləşdir
    0.71
     adolescents
    0.70
     cabinetry
    0.70
     recoverable
    0.69
     processus
    0.69
     COMPLET
    0.68
     stratégies
    0.68
    Activations Density 0.001%

    No Known Activations