© 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. 22-GEMMASCOPE-RES-131K
    7. 38836
    Prev
    Next
    INDEX
    Explanations

    lists of specific items

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

    The neuron specializes in spotting numeric expressions (measurements, quantities, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     had
    -0.94
    但我
    -0.83
     what
    -0.81
     single
    -0.80
     q
    -0.79
     has
    -0.78
    }]
    -0.78
     or
    -0.77
     expects
    -0.77
     when
    -0.75
    POSITIVE LOGITS
     extraordin
    0.95
     superbe
    0.93
     জন
    0.92
    uleiro
    0.90
    Autres
    0.90
    Specifica
    0.86
    และ
    0.86
     sonor
    0.85
     ennemi
    0.85
    Famille
    0.85
    Activations Density 0.069%

    No Known Activations