© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50301
    Prev
    Next
    INDEX
    Explanations

    timeline and deadlines

    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_34/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
    дэ
    -0.85
    ggia
    -0.82
    filed
    -0.79
     sentral
    -0.77
    ständige
    -0.75
    stehen
    -0.75
     Einstellungen
    -0.74
    ೃ
    -0.74
    θηκε
    -0.73
     проще
    -0.73
    POSITIVE LOGITS
     timeline
    5.63
     timelines
    4.91
     timetable
    4.41
     timeframe
    4.19
    timeline
    4.06
    Timeline
    3.94
     Timeline
    3.94
     timescale
    3.06
     timing
    2.98
     deadlines
    2.69
    Activations Density 0.052%

    No Known Activations