© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    Large Language Models

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

    The neuron strongly activates on capitalized domain-specific or organizational terms (e.g. names of fields, professional titles, societies, and proper nouns).

    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
    in
    0.29
     öst
    0.29
    س
    0.29
    atten
    0.28
    ost
    0.26
    ős
    0.26
    plaats
    0.26
    olm
    0.26
     nella
    0.25
     شرق
    0.25
    POSITIVE LOGITS
     construed
    0.30
     действи
    0.28
    <unused2130>
    0.27
    বিষয়
    0.26
     этот
    0.26
     других
    0.26
     потребности
    0.26
     modification
    0.26
     করপোর
    0.26
     sanded
    0.26
    Activations Density 0.053%

    No Known Activations