© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77618
    Prev
    Next
    INDEX
    Explanations

    runner-up positions and rankings

    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_34/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
     winning
    -1.34
    勝
    -1.28
     wins
    -1.20
     winners
    -1.08
     victory
    -1.03
     win
    -1.01
    胜
    -0.95
     winner
    -0.91
     victorious
    -0.90
    勝ち
    -0.90
    POSITIVE LOGITS
     runner
    2.91
     runners
    2.33
    Runner
    2.11
     Runner
    2.11
    runner
    2.00
    🥈
    1.95
     Runners
    1.78
    Runners
    1.70
     second
    1.59
    runners
    1.58
    Activations Density 0.045%

    No Known Activations