© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10261
    Prev
    Next
    INDEX
    Explanations

    some other

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

    The neuron detects indefinite quantifier words (e.g. “some,” “other,” “someone”).

    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
    殍
    -2.08
    僰
    -2.05
     zejména
    -2.02
     Dinas
    -2.00
     allerlei
    -1.98
    
    -1.98
    
    -1.92
    ༑
    -1.92
    ꯷
    -1.92
    mainly
    -1.91
    POSITIVE LOGITS
     from
    3.09
     what
    2.73
     with
    2.66
     that
    2.59
     at
    2.50
     had
    2.45
     which
    2.45
     one
    2.38
     could
    2.30
     those
    2.20
    Activations Density 0.016%

    No Known Activations