© 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. 22-GEMMASCOPE-RES-131K
    7. 72866
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

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

    The neuron strongly activates on capitalized proper names and acronyms—that is, named-entity tokens like people’s names or organization initials.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -2.14
     their
    -1.50
     if
    -1.35
     with
    -1.28
     in
    -1.27
     estekak
    -1.27
     which
    -1.24
     such
    -1.23
     both
    -1.22
     materia
    -1.20
    POSITIVE LOGITS
    Răspunde
    1.43
     REALLY
    1.25
     limpar
    1.24
     ativar
    1.23
     ACTUALLY
    1.23
     بسبب
    1.21
     sofrer
    1.20
     confirmó
    1.19
     kompati
    1.19
    Regarding
    1.18
    Activations Density 0.027%

    No Known Activations