© 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. 34-GEMMASCOPE-RES-131K
    7. 86925
    Prev
    Next
    INDEX
    Explanations

    shopping for or at

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

    The neuron detects occurrences of “shop” and its inflected forms (e.g., “shopping,” “shop around,” “shop for”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     продолжает
    -0.92
    ut
    -0.91
     operativa
    -0.86
    h
    -0.85
     भाग
    -0.85
    era
    -0.85
    ロナ
    -0.85
    jenige
    -0.84
    ora
    -0.84
    ont
    -0.84
    POSITIVE LOGITS
     for
    2.02
     at
    1.28
     online
    1.26
    🛍
    1.14
     from
    1.11
     persiapan
    1.06
     with
    1.02
     around
    1.01
     spree
    0.98
     convirtió
    0.96
    Activations Density 0.008%

    No Known Activations