© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    (a) or (1) style list items

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

    The neuron fires on parenthesized numerical citations or reference numbers (i.e. numbers appearing inside parentheses).

    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
    これにより
    0.48
     כי
    0.46
     thighs
    0.46
     तों
    0.45
    tti
    0.44
     tomto
    0.44
     ئەم
    0.43
    ů
    0.42
     kind
    0.42
    mata
    0.42
    POSITIVE LOGITS
    NYSE
    0.61
    CBS
    0.57
    HBO
    0.55
    CC
    0.55
     regalos
    0.55
    phabet
    0.54
    视频
    0.54
    ANCIS
    0.54
    ULTURAL
    0.54
    NASDAQ
    0.53
    Activations Density 0.023%

    No Known Activations