© 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. 25657
    Prev
    Next
    INDEX
    Explanations

    timing and sequence

    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
    TUAL
    -0.79
    揺
    -0.79
    ntomas
    -0.76
     Gläub
    -0.76
    exitRule
    -0.75
     Schluß
    -0.72
     besuchen
    -0.72
    そば
    -0.71
    otechnology
    -0.71
     Paleozoic
    -0.71
    POSITIVE LOGITS
     start
    1.52
     شروع
    1.20
     late
    1.16
     delayed
    1.13
     starting
    1.13
     시작
    1.09
    start
    1.05
     शुरू
    1.05
     delay
    1.03
     Start
    1.00
    Activations Density 0.095%

    No Known Activations