© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42908
    Prev
    Next
    INDEX
    Explanations

    metaphysical concepts and shop

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

    The neuron fires on words beginning with the “meta-” prefix (e.g. metaphysical, metafísica, metamodel).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Siehe
    -2.28
     Vgl
    -2.25
     abbiano
    -2.19
    薆
    -2.16
     aveva
    -2.13
    鸶
    -2.08
    内で
    -2.06
    轻易
    -2.06
     saranno
    -2.02
    看似
    -2.02
    POSITIVE LOGITS
    呖
    1.95
    
    1.92
    ?”
    1.91
    鑄
    1.84
    涐
    1.83
    떳
    1.77
     From
    1.77
    Bigr
    1.72
    ܜ
    1.72
     izle
    1.70
    Activations Density 0.006%

    No Known Activations