© 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. 22-GEMMASCOPE-RES-131K
    7. 35710
    Prev
    Next
    INDEX
    Explanations

    surrounding or centered

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

    The neuron responds to locative and spatial prepositions or adverbs (e.g. “around,” “about,” “centered,” “on,” “at”) indicating position or spatial relation.

    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
     wszystkich
    -1.31
     других
    -1.28
    millions
    -1.21
     millions
    -1.18
    thousands
    -1.17
     تمام
    -1.16
     innych
    -1.13
    hundreds
    -1.12
     multe
    -1.12
     모든
    -1.11
    POSITIVE LOGITS
     one
    1.32
     a
    1.19
     wrongdoing
    1.14
     central
    1.02
     focal
    0.96
     centred
    0.94
     centre
    0.91
     centres
    0.90
     eachother
    0.89
     informé
    0.87
    Activations Density 0.087%

    No Known Activations