© 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. 43371
    Prev
    Next
    INDEX
    Explanations

    members

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

    The neuron fires specifically on occurrences of the word “member” (in practice the plural “members”).

    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
    𓁹
    -3.22
    喾
    -2.73
    憷
    -2.72
     departamentos
    -2.66
    秾
    -2.61
     ciudadanos
    -2.61
    囟
    -2.59
    栳
    -2.58
    癰
    -2.56
     gobiernos
    -2.50
    POSITIVE LOGITS
    趼
    4.19
     For
    3.23
    狆
    3.11
     Undoubtedly
    3.02
    衎
    3.00
    淠
    3.00
     Regardless
    2.92
    ⢓
    2.91
    
    2.89
     Whether
    2.88
    Activations Density 0.027%

    No Known Activations