© 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. 45522
    Prev
    Next
    INDEX
    Explanations

    that is

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

    The main thing this neuron does is detect numeric tokens (i.e. 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
    Ито
    -0.79
     навчання
    -0.75
    アーティスト
    -0.75
     imageView
    -0.74
    Ос
    -0.73
    ühl
    -0.73
    ENTINA
    -0.71
    Дизайн
    -0.70
    Недо
    -0.69
    Tujuan
    -0.68
    POSITIVE LOGITS
     decir
    2.48
     cioè
    2.05
     heißt
    1.80
    ומר
    1.70
     есть
    1.48
     seja
    1.46
     znaczy
    1.39
    即
    1.39
    也就是
    1.33
    也就是说
    1.32
    Activations Density 0.036%

    No Known Activations