© 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. 73399
    Prev
    Next
    INDEX
    Explanations

    first up or next up

    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
    ↵
    -2.03
     kwamba
    -1.52
     its
    -1.50
     sababu
    -1.48
    every
    -1.48
     ця
    -1.38
     siku
    -1.38
     kuto
    -1.38
    <i>
    -1.36
     \&
    -1.35
    POSITIVE LOGITS
     must
    1.55
     coloris
    1.49
    bosity
    1.49
    嗩
    1.48
     ternura
    1.46
     blir
    1.46
     entendimiento
    1.45
    งิน
    1.43
     úč
    1.42
    ࿙
    1.42
    Activations Density 0.006%

    No Known Activations