© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75755
    Prev
    Next
    INDEX
    Explanations

    API authorization

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

    The neuron responds to numeric tokens (sequences of digits) 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
    LEMMA
    -0.77
     gutted
    -0.69
     accett
    -0.65
    λικά
    -0.65
    UIImage
    -0.64
    追
    -0.63
    yum
    -0.62
    罄
    -0.61
     imprison
    -0.61
    🤰
    -0.60
    POSITIVE LOGITS
    𝐠
    0.80
    чили
    0.74
    mism
    0.73
    ∝
    0.73
     township
    0.73
    Mait
    0.72
    dms
    0.70
    ρα
    0.70
    DMS
    0.70
     announcement
    0.69
    Activations Density 0.050%

    No Known Activations