© 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. 15386
    Prev
    Next
    INDEX
    Explanations

    2020 dates

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

    The neuron fires on tokens that are raw numbers or numeric sequences (i.e. any standalone digit strings).

    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
     Créez
    -1.09
    туга
    -1.08
    पित
    -1.02
    arschu
    -1.01
     donnés
    -0.95
     côté
    -0.95
     maș
    -0.94
     tuturor
    -0.94
     զ
    -0.94
    อาด
    -0.94
    POSITIVE LOGITS
     at
    1.41
     which
    1.39
     even
    1.28
    </h1>
    1.21
     césped
    1.17
    </h4>
    1.11
    անոթ
    1.07
    </b>
    1.05
     coronavirus
    1.03
     up
    1.02
    Activations Density 0.082%

    No Known Activations