© 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. 28213
    Prev
    Next
    INDEX
    Explanations

    locations and activities

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

    The neuron activates on descriptions of people clustered together around an object or workspace—e.g. a group huddled around a map table poring over details.

    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
     melalui
    -1.31
     through
    -1.27
     that
    -1.26
    celotti
    -1.23
     a
    -1.21
     poprzez
    -1.19
     via
    -1.17
     observaciones
    -1.12
    erobic
    -1.11
     fernández
    -1.09
    POSITIVE LOGITS
     with
    1.25
     blessure
    1.21
     categorie
    1.19
     gols
    1.18
     juf
    1.16
     tages
    1.16
     looking
    1.15
     boxe
    1.14
     lucre
    1.14
     tirs
    1.13
    Activations Density 0.047%

    No Known Activations