© 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. 67256
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

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

    The neuron fires strongly on the very first word of a new document or segment.

    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
     calendriers
    -2.52
     magnifiques
    -2.05
     retours
    -1.91
     logiciels
    -1.88
     cérami
    -1.86
     superbes
    -1.84
     eaux
    -1.83
     disques
    -1.83
     sentiers
    -1.80
     ongles
    -1.79
    POSITIVE LOGITS
    :
    2.27
     A
    2.03
     -
    2.02
     :
    1.87
    |
    1.78
     in
    1.77
     I
    1.71
     или
    1.67
     To
    1.66
     
    1.66
    Activations Density 0.457%

    No Known Activations