© 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. 71662
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    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
     often
    -1.75
     occasionally
    -1.73
     растений
    -1.59
    ׇ
    -1.59
    їна
    -1.58
     only
    -1.52
     always
    -1.49
    Ingrediente
    -1.48
     prêtres
    -1.43
     sometimes
    -1.41
    POSITIVE LOGITS
     сообщили
    2.00
    ଶ
    1.99
    🪛
    1.98
    дизайн
    1.93
     Wednesday
    1.91
    dây
    1.88
    𓃵
    1.87
     Monday
    1.83
     inalámbrica
    1.77
     Saturday
    1.75
    Activations Density 0.106%

    No Known Activations