© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99684
    Prev
    Next
    INDEX
    Explanations

    one or more

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

    The neuron fires strongly on expressions that denote a collection, in particular on the “group of …” construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ]&
    -1.41
     Arxivat
    -1.32
    ון
    -1.30
    variates
    -1.30
    createNewFile
    -1.28
     DOLLARS
    -1.23
    ции
    -1.21
     картины
    -1.20
    barrow
    -1.18
    iss
    -1.16
    POSITIVE LOGITS
     such
    1.73
     these
    1.70
     those
    1.56
     groups
    1.45
     solchen
    1.40
     this
    1.34
     bestimmten
    1.31
    这样
    1.30
     таких
    1.27
     construcciones
    1.26
    Activations Density 0.087%

    No Known Activations