© 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. 15334
    Prev
    Next
    INDEX
    Explanations

    ranges or intervals

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

    The neuron fires on the word “to” when it’s used to connect numeric or date ranges (e.g. “1867 to 1930,” “23.03 to 200.43 Ma”).

    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
     mtu
    -1.73
     vya
    -1.70
     lakini
    -1.65
     nini
    -1.64
    ik
    -1.64
     watu
    -1.63
    疍
    -1.63
    簓
    -1.61
     siku
    -1.60
     tetapi
    -1.59
    POSITIVE LOGITS
    徇
    1.98
    訛
    1.84
    poir
    1.84
     anerkannt
    1.83
    遴
    1.80
     origins
    1.80
     Ihren
    1.75
     sicheren
    1.70
    亊
    1.67
     experience
    1.66
    Activations Density 0.039%

    No Known Activations