© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    of the

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

    The neuron fires on phrases that specify numerical selection of items—e.g. “one or more of,” “one or both of,” “one or all of the following.”

    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
    Some
    -2.00
    Because
    -1.98
    Regardless
    -1.97
     one
    -1.94
    Unlike
    -1.87
    One
    -1.85
    Even
    -1.85
    Though
    -1.84
    Despite
    -1.81
    Perhaps
    -1.81
    POSITIVE LOGITS
    蛱
    1.80
    ೢ
    1.74
     sprüche
    1.70
     mostrarán
    1.66
    痨
    1.58
     ní
    1.57
    瘊
    1.56
    跸
    1.56
    𐌱
    1.53
    姤
    1.52
    Activations Density 0.010%

    No Known Activations