© 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. 22-GEMMASCOPE-RES-131K
    4. 39856
    Prev
    Next
    INDEX
    Explanations

    date and time information

    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
     ПРЕ
    -0.87
    worden
    -0.82
    леко
    -0.81
    VIAF
    -0.80
     Clan
    -0.80
     alimenti
    -0.80
     schoenen
    -0.79
     bagi
    -0.79
    記録
    -0.77
    年齢
    -0.75
    POSITIVE LOGITS
     time
    1.47
     deadlines
    1.23
     timeframe
    1.13
     period
    1.10
     hours
    1.10
     calendar
    1.09
     timing
    1.09
     timelines
    1.09
     timeline
    1.09
     duration
    1.08
    Activations Density 0.057%

    No Known Activations