© 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. 12048
    Prev
    Next
    INDEX
    Explanations

    language and topic labels

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

    The neuron fires on mentions of company, product, and material names—that is, brand names and technical entity terms.

    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
     হইতেছিল
    1.06
     ؟
    0.99
     চাহিল
    0.93
     করিতেছিল
    0.92
     Сколько
    0.91
     Акысыз
    0.89
     Спорттук
    0.89
    ayutt
    0.86
     Assignments
    0.86
    ulfanyl
    0.85
    POSITIVE LOGITS
    1
    1.16
    の
    1.14
    に
    1.12
    を
    1.11
    2
    1.09
    6
    1.05
    が
    1.05
    への
    1.03
    8
    1.02
    （
    1.02
    Activations Density 0.004%

    No Known Activations