© 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. 34-GEMMASCOPE-RES-131K
    7. 79078
    Prev
    Next
    INDEX
    Explanations

    Names of people

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

    The neuron fires on the beginnings of capitalized character or person names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     at
    -1.64
     in
    -1.52
     !!!
    -1.45
     this
    -1.43
     on
    -1.41
     sehr
    -1.34
     so
    -1.33
    Often
    -1.33
     (
    -1.27
     !!
    -1.24
    POSITIVE LOGITS
     ſol
    1.77
     unbelievably
    1.66
     unn
    1.65
     sooo
    1.58
     insanely
    1.52
     soooo
    1.48
    IIII
    1.44
    ervant
    1.41
    tening
    1.39
     eſſ
    1.38
    Activations Density 0.006%

    No Known Activations