© 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. 22-GEMMASCOPE-RES-131K
    4. 68823
    Prev
    Next
    INDEX
    Explanations

    collections and collecting

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

    The main thing this neuron does is find words and phrases about collecting or collections (e.g., “collecting,” “collection,” “collector,” “display”).

    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
     with
    -1.68
     on
    -1.58
     at
    -1.55
     as
    -1.50
     in
    -1.49
     provided
    -1.48
     four
    -1.48
     three
    -1.47
     provide
    -1.39
     operations
    -1.38
    POSITIVE LOGITS
     magnifiques
    1.55
     колек
    1.48
     véritables
    1.45
     목록
    1.45
     musées
    1.45
     acheté
    1.33
     rassemb
    1.33
     kolek
    1.32
     réun
    1.32
     récomp
    1.30
    Activations Density 0.036%

    No Known Activations