© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20238
    Prev
    Next
    INDEX
    Explanations

    words starting with Ver

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

    This neuron responds to the three-letter sequence “Ver” (e.g. in words like Vertica, Verón, Version, 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
    蝋
    -2.83
     Hinblick
    -2.70
     estekak
    -2.61
    ologiques
    -2.58
     белом
    -2.56
    灩
    -2.56
    浤
    -2.53
     gustaMe
    -2.50
    pecabe
    -2.47
     Gegensatz
    -2.45
    POSITIVE LOGITS
    1
    4.25
    3
    3.77
    0
    3.58
    Of
    3.55
    2
    3.55
    6
    3.45
    5
    3.44
    9
    3.39
    7
    3.38
    \
    3.14
    Activations Density 0.003%

    No Known Activations