© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12284
    Prev
    Next
    INDEX
    Explanations

    expressing sentiment or opinion

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

    The neuron strongly fires on multiword verb–particle constructions (phrasal verbs).

    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
     bahan
    0.79
     atau
    0.76
     plugins
    0.75
    ?
    0.75
     fulfils
    0.71
     tenho
    0.70
     emits
    0.70
     libs
    0.69
     dan
    0.69
     plugin
    0.69
    POSITIVE LOGITS
    谴
    0.86
    道歉
    0.80
     જણાવ્યું
    0.76
     назвал
    0.76
    譴
    0.75
    ：「
    0.73
    বের
    0.72
    看法
    0.71
    ：“
    0.71
    自殺
    0.71
    Activations Density 0.240%

    No Known Activations