© 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. 22-GEMMASCOPE-RES-131K
    7. 40287
    Prev
    Next
    INDEX
    Explanations

    plot, segment, pattern

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

    The neuron specializes in spotting tokens that contain numeric literals (digits or decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     velho
    -0.83
    робі
    -0.81
     Me
    -0.80
    sym
    -0.78
     or
    -0.77
     ’
    -0.77
    サート
    -0.76
     Or
    -0.75
     OR
    -0.75
     fortale
    -0.74
    POSITIVE LOGITS
     aceptación
    0.94
     각
    0.93
    UnknownFieldSet
    0.90
     tinder
    0.89
    hlás
    0.86
    gogo
    0.86
    IVAN
    0.86
    BeginInit
    0.86
    ávání
    0.84
    ВА
    0.83
    Activations Density 0.022%

    No Known Activations