© 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. 48070
    Prev
    Next
    INDEX
    Explanations

    product names

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

    The neuron strongly activates on numeric tokens (digits and multi‐digit numbers), i.e. it detects numbers and numeric measurements 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
     listen
    -1.00
     watch
    -0.99
     listening
    -0.80
     watches
    -0.79
     مُعرِّف
    -0.75
     perhaps
    -0.72
     watched
    -0.70
     गई
    -0.69
    养殖
    -0.69
     probably
    -0.69
    POSITIVE LOGITS
    有利
    0.90
    Kurs
    0.89
    ARON
    0.81
     الصف
    0.80
     écrire
    0.78
    council
    0.78
     égard
    0.77
     Méri
    0.77
    Courses
    0.75
     juſt
    0.75
    Activations Density 0.021%

    No Known Activations