© 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. 61459
    Prev
    Next
    INDEX
    Explanations

    Willie Mataka

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

    The neuron fires on numeric tokens (digit sequences), especially numbers in code or SVG path data.

    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
     cómoda
    -1.59
     exclusivas
    -1.55
     zio
    -1.51
     atractiva
    -1.48
     préstamos
    -1.45
     valioso
    -1.42
     komfor
    -1.39
    なども
    -1.39
     piaci
    -1.39
     cordón
    -1.38
    POSITIVE LOGITS
    .
    1.77
    我没有
    1.63
    一つの
    1.49
     Although
    1.45
     is
    1.44
                   
    1.43
    шая
    1.42
     смета
    1.40
    我没
    1.39
    するため
    1.38
    Activations Density 0.009%

    No Known Activations