© 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. 34-GEMMASCOPE-RES-131K
    4. 622
    Prev
    Next
    INDEX
    Explanations

    bodily health and biology

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

    descriptions of skin care products and their health benefits.

    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_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
     their
    -0.97
    炷
    -0.95
    ;
    -0.94
    を選択します
    -0.93
    Exemplo
    -0.93
    :
    -0.92
    ının
    -0.90
    infty
    -0.88
    ított
    -0.88
     destructor
    -0.88
    POSITIVE LOGITS
     while
    1.74
     by
    1.62
     and
    1.50
     naturally
    1.41
     due
    1.40
    while
    1.24
     thanks
    1.23
     WHILE
    1.23
     Ră
    1.17
     therefore
    1.16
    Activations Density 0.039%

    No Known Activations