© 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. 7803
    Prev
    Next
    INDEX
    Explanations

    you might

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

    The neuron primarily activates on auxiliary or linking verbs (especially forms of “to be” like is/was and modals like can).

    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
     reportedly
    0.91
    据说
    0.85
     считают
    0.75
     says
    0.71
     கருதப்படுகிறது
    0.70
    显得
    0.69
     сказали
    0.69
     известно
    0.69
     знают
    0.69
     diketahui
    0.67
    POSITIVE LOGITS
     Acest
    0.81
     acest
    0.76
    必须要
    0.71
     potrzeb
    0.70
     benötigen
    0.69
    ត្រូវការ
    0.69
     lacked
    0.67
     needed
    0.66
     dette
    0.66
     thisStudent
    0.66
    Activations Density 0.802%

    No Known Activations