© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64679
    Prev
    Next
    INDEX
    Explanations

    doubling size

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

    The neuron fires on numeric tokens—i.e. it spots numbers (digit sequences) 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
    borg
    -0.74
     आई
    -0.73
    時期
    -0.63
     pol
    -0.63
     Ol
    -0.62
    划
    -0.60
    UMS
    -0.60
     DOS
    -0.60
     أحد
    -0.60
     Leo
    -0.60
    POSITIVE LOGITS
     doubling
    0.81
     unvaccinated
    0.75
     dvoj
    0.74
    harga
    0.73
     segn
    0.72
     Calderón
    0.71
    Calvin
    0.71
    glove
    0.68
    Caring
    0.68
     Sioux
    0.68
    Activations Density 0.071%

    No Known Activations