© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128204
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" or "exist"

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

    The neuron fires on tokens representing numbers or numeric quantities (e.g. “14,” “137,” “225,” “32,” “49.75,” etc.).

    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
     utilizada
    -1.88
    킁
    -1.85
    栊
    -1.81
    ㈯
    -1.80
    ことができました
    -1.80
    
    -1.79
     alojamientos
    -1.79
    葙
    -1.78
     suministros
    -1.77
     neumáticos
    -1.75
    POSITIVE LOGITS
     with
    3.28
     by
    2.70
     an
    2.23
     one
    2.14
     (
    1.98
     in
    1.85
     a
    1.82
     Those
    1.82
     on
    1.80
     If
    1.70
    Activations Density 0.024%

    No Known Activations