© 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. 73070
    Prev
    Next
    INDEX
    Explanations

    breaking and injury

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

    The neuron is detecting numeric tokens—numbers and decimal measurements.

    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
    𐀀
    -1.23
     disques
    -1.21
     jednak
    -1.18
     publiques
    -1.16
    quirer
    -1.16
     juridiques
    -1.16
     bulunabilir
    -1.16
     pourront
    -1.15
     häufiger
    -1.14
     ۱۵
    -1.12
    POSITIVE LOGITS
     during
    1.79
     went
    1.35
     with
    1.34
     took
    1.31
     nearly
    1.29
     four
    1.28
     two
    1.27
     there
    1.27
     choosing
    1.26
     gave
    1.23
    Activations Density 0.325%

    No Known Activations