© 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. 129230
    Prev
    Next
    INDEX
    Explanations

    subscription

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

    This neuron fires on occurrences of the word “Subscription.”

    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
    埽
    -3.09
    鵟
    -3.09
     unſ
    -2.92
    
    -2.89
     uſ
    -2.78
     但
    -2.73
     stalwart
    -2.73
    狨
    -2.72
     firent
    -2.64
     faisaient
    -2.64
    POSITIVE LOGITS
    ).
    3.84
    ↵
    3.31
    ’
    3.23
    K
    2.95
    a
    2.83
    Q
    2.77
    d
    2.73
    g
    2.73
    酲
    2.70
    R
    2.64
    Activations Density 0.004%

    No Known Activations