© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7181
    Prev
    Next
    INDEX
    Explanations

    select from options

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

    The neuron activates on numeric tokens (integers or decimals) representing quantities, prices, ranges, or counts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -1.95
     ‘
    -1.94
     U
    -1.69
     S
    -1.68
         
    -1.64
     D
    -1.63
     C
    -1.62
     \
    -1.58
     
    -1.58
     you
    -1.57
    POSITIVE LOGITS
    苤
    1.87
     himſelf
    1.87
     chêne
    1.77
     obſ
    1.73
    垕
    1.70
     multicolore
    1.66
     ſou
    1.66
    韡
    1.65
     municipales
    1.65
     humeur
    1.63
    Activations Density 0.015%

    No Known Activations