© 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. 33199
    Prev
    Next
    INDEX
    Explanations

    place names and entities

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

    The neuron responds to numeric tokens—quantities, measurements, years, population figures, percentages, etc.

    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
     both
    -1.16
     get
    -1.11
     this
    -1.10
     any
    -1.09
    expiresIn
    -1.08
     most
    -1.06
     systems
    -1.05
     Uniwers
    -1.05
     all
    -1.02
     only
    -1.01
    POSITIVE LOGITS
     hué
    1.20
    Jueves
    1.13
    Tors
    1.09
     búsquedas
    1.09
     mensaj
    1.08
    綣
    1.07
     poesía
    1.05
    蠲
    1.05
     participer
    1.05
     vii
    1.05
    Activations Density 0.001%

    No Known Activations