© 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. 109465
    Prev
    Next
    INDEX
    Explanations

    Stokes V, line of sight

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

    The neuron activates on numeric tokens and digit sequences (i.e. numbers).

    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
     NTS
    -0.80
     Baroness
    -0.73
    inys
    -0.70
    どく
    -0.69
    WebpackPlugin
    -0.66
    inistro
    -0.66
     sudo
    -0.66
     broiler
    -0.65
     Displays
    -0.63
    ensis
    -0.63
    POSITIVE LOGITS
     lodging
    0.75
    красный
    0.69
     Holy
    0.68
    secuted
    0.68
    ILO
    0.67
     Literary
    0.67
    紫
    0.67
     வெ
    0.66
    ラリー
    0.66
    USING
    0.66
    Activations Density 0.047%

    No Known Activations