© 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. 28154
    Prev
    Next
    INDEX
    Explanations

    dairy products

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

    food items, particularly dairy products and spreads like cheese, butter, and cream.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    L
    -1.44
    ho
    -1.37
    $,
    -1.31
    C
    -1.29
     intervenciones
    -1.27
     deines
    -1.26
    ne
    -1.23
    P
    -1.23
     a
    -1.22
    V
    -1.22
    POSITIVE LOGITS
    Sebelum
    1.15
    Berat
    1.14
    咱们
    1.13
    极为
    1.13
    playera
    1.11
     آور
    1.11
    ることができます
    1.11
    NOTAS
    1.11
    Día
    1.09
     Automó
    1.09
    Activations Density 0.024%

    No Known Activations