© 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. 10-GEMMASCOPE-RES-131K
    4. 87354
    Prev
    Next
    INDEX
    Explanations

    Email replies or subjects

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

    The neuron detects numeric tokens (especially decimal numbers or measured values).

    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
     this
    -2.69
     it
    -2.06
     the
    -1.70
     your
    -1.67
     our
    -1.53
     where
    -1.52
     these
    -1.51
     in
    -1.49
     there
    -1.48
     before
    -1.45
    POSITIVE LOGITS
    ingale
    1.67
     {
    
    1.65
    neous
    1.61
    isait
    1.58
    gering
    1.56
    agerie
    1.55
    llllll
    1.51
    emissions
    1.46
    omato
    1.46
    iferous
    1.45
    Activations Density 0.340%

    No Known Activations