© 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. 3982
    Prev
    Next
    INDEX
    Explanations

    code blocks and definitions

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

    The neuron specializes in detecting the “+” token used to mark added lines (e.g. in code diffs or patch files).

    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
    Y
    0.64
    lation
    0.61
    ru
    0.57
    HOR
    0.56
    izations
    0.55
     waveguides
    0.55
    umes
    0.55
    N
    0.55
    乃至
    0.54
    J
    0.54
    POSITIVE LOGITS
     partecipare
    0.60
    нт
    0.57
     ใช้
    0.57
     Кстати
    0.55
    ইডি
    0.54
     retten
    0.53
     Chỉ
    0.52
    ючи
    0.51
    焽
    0.51
     Thực
    0.51
    Activations Density 0.000%

    No Known Activations