© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97867
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

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

    The neuron fires on four-digit numerals (i.e. large numbers) appearing in math questions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.88
    。。。。
    -0.84
     that
    -0.80
     differing
    -0.78
     challenging
    -0.77
    PILE
    -0.77
    كتور
    -0.76
    閬
    -0.76
    laması
    -0.76
     budapest
    -0.76
    POSITIVE LOGITS
    界
    0.84
    totally
    0.80
    hopefully
    0.77
     итого
    0.77
    Immer
    0.71
     gesch
    0.71
    heureusement
    0.69
    ModelAndView
    0.69
     Hades
    0.69
    ROSS
    0.68
    Activations Density 0.000%

    No Known Activations