© 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. 105353
    Prev
    Next
    INDEX
    Explanations

    names and dates after specific words

    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
     hivyo
    -1.81
     kuhusu
    -1.73
     kwamba
    -1.57
     kutumia
    -1.55
    Răspunde
    -1.54
     utafiti
    -1.47
     yaklaşık
    -1.46
    もあって
    -1.44
     unaweza
    -1.43
    ündig
    -1.41
    POSITIVE LOGITS
     had
    1.91
     during
    1.63
     at
    1.55
     one
    1.48
     have
    1.47
     after
    1.38
    」「
    1.35
     in
    1.34
     all
    1.32
     filmi
    1.23
    Activations Density 0.019%

    No Known Activations