© 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. 34-GEMMASCOPE-RES-131K
    7. 98826
    Prev
    Next
    INDEX
    Explanations

    cars, horse races, code

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

    The neuron flags numeric data (e.g. digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ard
    -0.79
     famine
    -0.78
     él
    -0.75
    AddArg
    -0.75
    カブ
    -0.73
    пит
    -0.73
     연
    -0.72
     Disk
    -0.72
    弛
    -0.71
    馄
    -0.70
    POSITIVE LOGITS
    Anni
    0.80
     anhyd
    0.79
     cammin
    0.77
     isolamento
    0.74
    黄
    0.73
     speciale
    0.72
     églises
    0.72
    NPP
    0.72
    Blogs
    0.72
     potere
    0.72
    Activations Density 0.012%

    No Known Activations