© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67383
    Prev
    Next
    INDEX
    Explanations

    Veronica or alcoholic health

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

    The neuron activates for words or phrases related to alcoholism and alcohol-related conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the specific token “Veronica.”

    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
    1
    -3.64
    -
    -3.45
    ?
    -3.27
    ↵
    -3.05
    THE
    -2.86
    2
    -2.83
     
    -2.80
    4
    -2.78
    8
    -2.59
    ”
    -2.56
    POSITIVE LOGITS
    служба
    2.56
     protože
    2.52
    我们要
    2.50
     册
    2.47
    锨
    2.44
    ֢
    2.41
    獁
    2.41
    eada
    2.41
    疴
    2.39
    Pgina
    2.38
    Activations Density 0.004%

    No Known Activations