© 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. 73111
    Prev
    Next
    INDEX
    Explanations

    opening sequences and starts

    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
     infine
    -1.06
    ürme
    -0.98
    最终
    -0.98
    ventions
    -0.94
    cinogenicity
    -0.94
    rupulous
    -0.93
    closer
    -0.93
    ieť
    -0.91
    简约
    -0.90
    autres
    -0.90
    POSITIVE LOGITS
     initial
    2.17
     start
    1.89
     early
    1.85
     beginning
    1.73
     starting
    1.66
     first
    1.65
     нача
    1.61
     immediately
    1.59
     시작
    1.57
     begin
    1.55
    Activations Density 0.080%

    No Known Activations