© 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. 108160
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

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

    The neuron activates on numeric tokens (numbers or 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
    ocarditis
    -1.17
    Ayrıca
    -1.13
     bojo
    -1.08
     expédié
    -1.06
    Perhaps
    -1.05
    +=(
    -1.02
     також
    -1.02
     obrazy
    -1.00
     what
    -1.00
    Maybe
    -1.00
    POSITIVE LOGITS
     choices
    1.25
     CORRECT
    1.05
     options
    1.05
    ar
    1.05
     Option
    1.03
     alternatives
    1.02
     вариан
    1.01
     OPTION
    0.99
     neither
    0.96
     option
    0.96
    Activations Density 0.006%

    No Known Activations