© 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. 10-GEMMASCOPE-RES-131K
    7. 41749
    Prev
    Next
    INDEX
    Explanations

    names followed by specific entities

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

    The neuron fires on standalone numeric tokens (i.e. numbers such as years or other multi‐digit figures).

    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
     With
    -2.64
    ︕
    -2.63
     définiti
    -2.63
    慙
    -2.59
    
    -2.53
    шего
    -2.47
     問
    -2.42
     direttamente
    -2.39
     hinting
    -2.39
    由于
    -2.33
    POSITIVE LOGITS
    .
    3.13
     pewno
    2.69
     
    2.56
     concern
    2.50
     impetus
    2.48
    in
    2.39
    as
    2.33
    牁
    2.31
     contrô
    2.31
    F
    2.25
    Activations Density 0.004%

    No Known Activations