© 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. 22-GEMMASCOPE-RES-131K
    7. 72067
    Prev
    Next
    INDEX
    Explanations

    winning team

    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
     개
    -0.89
    ()
    -0.88
    完整的
    -0.88
    8
    -0.87
    ciąż
    -0.87
    ござい
    -0.85
     площа
    -0.85
     أن
    -0.84
     personnelles
    -0.82
     enfrenta
    -0.82
    POSITIVE LOGITS
     team
    1.44
    teamId
    1.05
    ご予約
    1.04
     avião
    1.04
    )=\
    1.02
    équipe
    1.01
    ሠ
    1.00
     group
    1.00
    Наталья
    0.98
     doa
    0.97
    Activations Density 0.089%

    No Known Activations