© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57523
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and numbers

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

    This neuron is essentially “dead” in these samples—it does not activate on any token here.

    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
     this
    -1.99
     also
    -1.77
     to
    -1.66
     также
    -1.64
     not
    -1.55
     contextLoads
    -1.50
     or
    -1.46
    ://
    -1.43
     inoltre
    -1.43
    -1.41
    POSITIVE LOGITS
    
    1.55
     colonnes
    1.52
    ఽ
    1.51
     dát
    1.45
     degrés
    1.41
     variedade
    1.39
     beneficiario
    1.38
     wektor
    1.38
     –
    1.37
     EIGHT
    1.32
    Activations Density 0.012%

    No Known Activations