© 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. 6097
    Prev
    Next
    INDEX
    Explanations

    longer distances

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

    The neuron fires on single-word headings or topic‐label tokens (e.g. “addresses,” “writes,” “wired,” “native,” “space,” “structure”) that introduce or name a new section.

    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
    ो
    0.81
    渋谷
    0.78
    р
    0.77
    ר
    0.76
    er
    0.73
    ার
    0.73
    ו
    0.70
    撻
    0.68
    娅
    0.66
    ر
    0.66
    POSITIVE LOGITS
     monopolies
    0.87
     Pampl
    0.86
     énon
    0.83
    एफटी
    0.82
     koristi
    0.81
     baits
    0.80
     jedna
    0.80
     teléfonos
    0.79
     tropomyosin
    0.79
     piles
    0.79
    Activations Density 0.000%

    No Known Activations