© 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. 61491
    Prev
    Next
    INDEX
    Explanations

    trade unionist

    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
    \
    -1.55
     addition
    -1.38
     много
    -1.37
    só
    -1.34
    tığı
    -1.33
    六年
    -1.30
     acknowledgment
    -1.30
    т
    -1.30
    唯一的
    -1.30
     Our
    -1.27
    POSITIVE LOGITS
    ieteur
    1.72
     as
    1.61
    </h5>
    1.60
    lahraga
    1.54
     ?",
    1.52
    飆
    1.44
    驭
    1.41
    的一声
    1.40
    meneu
    1.40
    cony
    1.38
    Activations Density 0.083%

    No Known Activations