© 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. 100461
    Prev
    Next
    INDEX
    Explanations

    created by on date

    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
    スポンサーリンク
    -1.98
    年から
    -1.91
     diki
    -1.84
     kapak
    -1.84
     Buka
    -1.84
    焢
    -1.78
     kapas
    -1.73
     senin
    -1.71
     rengi
    -1.70
     quinto
    -1.66
    POSITIVE LOGITS
     is
    2.55
     ~
    1.79
     time
    1.54
     nació
    1.48
     Gedichte
    1.48
     IN
    1.48
     všech
    1.46
     D
    1.44
    }{
    1.42
     TO
    1.42
    Activations Density 0.005%

    No Known Activations