© 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. 59922
    Prev
    Next
    INDEX
    Explanations

    South Carolina, Chyna, page, unlock

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

    The neuron strongly activates on proper‐name and numeric tokens, i.e. named entities (people, places, organizations) and 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
     分类
    -0.84
     pins
    -0.78
     Danube
    -0.75
    cepcion
    -0.73
    çim
    -0.70
    caja
    -0.68
    飪
    -0.68
     forward
    -0.68
    numericUpDown
    -0.67
     justifying
    -0.67
    POSITIVE LOGITS
     Blink
    0.79
    锌
    0.76
    EDEN
    0.75
     PDB
    0.74
     Southampton
    0.73
    🎥
    0.73
     trois
    0.71
    BAN
    0.70
    REQ
    0.69
    Emil
    0.69
    Activations Density 0.010%

    No Known Activations