© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14113
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    The neuron fires strongly on tokens that are part of formal reference or contact‐info metadata—especially author names and initials (e.g. “J.,” “Clifton,” “Michael W.”) and similar citation elements.

    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
    ске
    0.79
    ounded
    0.76
    ounds
    0.74
    ет
    0.73
     choses
    0.72
    ezi
    0.72
    лет
    0.71
     לך
    0.70
    sa
    0.70
    смо
    0.70
    POSITIVE LOGITS
    ]";
    0.89
    斓
    0.78
     RIGHTS
    0.77
    LPTMR
    0.75
    Архівовано
    0.75
    胳
    0.73
    亟
    0.73
    ]&
    0.73
    目录下
    0.72
     Symfony
    0.71
    Activations Density 0.001%

    No Known Activations