© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70094
    Prev
    Next
    INDEX
    Explanations

    the word majority

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

    The neuron spotlights statistical‐quantity expressions—especially proportions (e.g. “a majority of X” and accompanying percentages or numeric counts).

    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
     a
    -1.67
    the
    -1.66
    iencies
    -1.63
    埽
    -1.58
    </u>
    -1.58
    </h5>
    -1.55
    -1.52
     trabajadores
    -1.48
    <b>
    -1.44
     columnas
    -1.43
    POSITIVE LOGITS
     of
    1.89
     hvid
    1.60
    jdons
    1.58
    
    1.57
     svart
    1.57
    vejec
    1.53
     tæt
    1.50
     andet
    1.50
    Determining
    1.49
    )$,
    1.48
    Activations Density 0.003%

    No Known Activations