© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    introduction or overview

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

    The neuron activates on tokens that are part of bibliographic citations or book/article titles in a references section.

    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
    Topic
    0.37
    Lesson
    0.36
    Fuck
    0.34
    ア
    0.34
    ジェ
    0.33
    Excuse
    0.33
    Episode
    0.32
    Theme
    0.32
    Murder
    0.32
    Potion
    0.32
    POSITIVE LOGITS
     ব্যবহৃত
    0.38
     것입니다
    0.37
     additions
    0.36
     indications
    0.36
     tenths
    0.35
    <unused2164>
    0.35
     usable
    0.35
     것으로
    0.35
     prerog
    0.35
     adherent
    0.35
    Activations Density 0.064%

    No Known Activations