© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102616
    Prev
    Next
    INDEX
    Explanations

    player position abbreviations

    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
    ᴋ
    -1.45
    tiske
    -1.43
     sint
    -1.37
    henden
    -1.30
     seminario
    -1.26
     digitized
    -1.25
    륭
    -1.23
    chenden
    -1.23
    であった
    -1.20
     hazır
    -1.20
    POSITIVE LOGITS
     and
    1.94
     verhind
    1.48
    gemar
    1.41
    percentage
    1.40
    𓋼
    1.33
    mudah
    1.33
    moin
    1.28
     verminder
    1.23
    keren
    1.22
    
    1.22
    Activations Density 0.016%

    No Known Activations