© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    other and subsequent noun

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

    The neuron strongly activates on the word “Other,” effectively spotting section‐leading “Other” headings or list introductions.

    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
    ל
    1.25
    TA
    1.17
    ट
    1.10
    OR
    1.05
    ap
    1.05
    TUR
    1.02
    ina
    1.01
    ouvrir
    1.01
    TY
    1.00
    ﺎ
    1.00
    POSITIVE LOGITS
    worldly
    1.38
     FAQs
    1.04
     Aspects
    1.02
     yandan
    1.02
    меры
    1.02
     Considerations
    1.02
     alternatives
    1.01
     notables
    0.97
    apeutics
    0.97
     factors
    0.96
    Activations Density 0.000%

    No Known Activations