© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15535
    Prev
    Next
    INDEX
    Explanations

    identification and regulations

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

    The neuron activates on numeric tokens—especially measurements or decimal 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_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
    着一个
    -1.32
     speziellen
    -1.14
     продъл
    -1.02
     merkwür
    -1.01
     Heute
    -1.01
     opět
    -1.00
     zusätzlichen
    -0.99
    đi
    -0.98
     ❤️
    -0.97
     üblichen
    -0.97
    POSITIVE LOGITS
    ení
    1.33
    </b>
    1.30
     iedere
    1.26
     tikai
    1.22
     iedereen
    1.16
     himſelf
    1.13
    ierter
    1.10
    prender
    1.07
     påver
    1.05
    istolet
    1.05
    Activations Density 0.054%

    No Known Activations