© 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. 10-GEMMASCOPE-RES-131K
    7. 11996
    Prev
    Next
    INDEX
    Explanations

    shipping services and couriers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    "");
    -1.44
     unſ
    -1.41
     estava
    -1.40
     länder
    -1.37
    љу
    -1.36
    </caption>
    -1.34
    concentration
    -1.34
    lity
    -1.33
    ки
    -1.30
    espero
    -1.30
    POSITIVE LOGITS
     both
    1.43
    when
    1.37
     when
    1.37
     zahlreiche
    1.36
     From
    1.32
     our
    1.29
     彈
    1.27
    #
    1.27
     metamorphosis
    1.27
     those
    1.26
    Activations Density 0.021%

    No Known Activations