© 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. 22-GEMMASCOPE-RES-131K
    4. 67385
    Prev
    Next
    INDEX
    Explanations

    fees, dividends, licenses, refunds

    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_22/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
     decidiu
    -1.27
     pediu
    -1.23
     krę
    -1.22
     then
    -1.20
    叻
    -1.16
     acabou
    -1.09
     fiquei
    -1.09
     powietrza
    -1.07
    </h4>
    -1.05
     między
    -1.05
    POSITIVE LOGITS
     to
    2.33
     for
    1.67
     by
    1.48
     faſt
    1.44
     in
    1.32
    任何人
    1.31
     conva
    1.31
     which
    1.27
     based
    1.24
    гласно
    1.23
    Activations Density 0.049%

    No Known Activations