© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71013
    Prev
    Next
    INDEX
    Explanations

    announcement or future events

    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
    독
    -0.98
     作り
    -0.94
     regularly
    -0.91
     방법
    -0.91
    例えば
    -0.90
    その後
    -0.90
     đà
    -0.90
     Czechos
    -0.88
     bairro
    -0.87
     each
    -0.87
    POSITIVE LOGITS
     announcement
    1.94
     will
    1.79
     announced
    1.55
     будет
    1.17
    acağı
    1.16
     announce
    1.13
     announcements
    1.13
    announcement
    1.12
     Announcement
    1.09
     mengumumkan
    1.09
    Activations Density 0.082%

    No Known Activations