© 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. 99622
    Prev
    Next
    INDEX
    Explanations

    so that

    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
     เขา
    -1.84
    ’，
    -1.79
     réfugiés
    -1.64
     nahil
    -1.63
     mété
    -1.57
     มัน
    -1.52
    眥
    -1.52
     its
    -1.51
     puni
    -1.50
     protagonisti
    -1.50
    POSITIVE LOGITS
    </h3>
    2.25
     glimpse
    1.70
    </strong>
    1.60
     awful
    1.60
     guessing
    1.58
     Therefore
    1.57
     unbe
    1.56
    ،
    1.55
    したが
    1.52
     entail
    1.50
    Activations Density 0.009%

    No Known Activations