© 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. 90217
    Prev
    Next
    INDEX
    Explanations

    protobuf messages

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

    The neuron activates on standalone numeric tokens (i.e. literals made up of digits).

    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
     contaminated
    -0.77
    初代
    -0.73
    切り
    -0.72
    Bacterial
    -0.72
     Socialist
    -0.70
    tischer
    -0.69
     верно
    -0.69
    люсы
    -0.68
     yeah
    -0.67
    Cler
    -0.66
    POSITIVE LOGITS
    PB
    1.20
     messages
    1.20
     PB
    1.16
     Pb
    1.14
    pb
    1.13
    messages
    1.13
     Messages
    1.07
    msg
    1.04
     message
    1.00
     Proto
    0.95
    Activations Density 0.029%

    No Known Activations