© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54057
    Prev
    Next
    INDEX
    Explanations

    convolutional layer parameters

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

    The main thing this neuron does is detect numeric literals (tokens consisting of digits).

    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
     Renault
    -0.84
     mari
    -0.71
     apricot
    -0.69
    谧
    -0.68
    gesamt
    -0.68
    itaries
    -0.68
    壬
    -0.68
    meiras
    -0.67
    sists
    -0.67
    ضاء
    -0.67
    POSITIVE LOGITS
     filters
    1.20
     channels
    1.18
     channel
    1.13
    filters
    1.05
    channel
    1.01
    channels
    0.88
     récents
    0.81
     tegens
    0.80
    ERD
    0.79
    Filters
    0.78
    Activations Density 0.009%

    No Known Activations