© 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. 68827
    Prev
    Next
    INDEX
    Explanations

    future events or outcomes

    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
     always
    -1.06
     всегда
    -0.98
    always
    -0.90
    ிறது
    -0.90
    iaus
    -0.89
    сии
    -0.86
     Mieter
    -0.86
    何故
    -0.85
    愛用
    -0.84
    evolution
    -0.82
    POSITIVE LOGITS
     will
    2.80
     hopefully
    1.91
     now
    1.91
     Hopefully
    1.77
     future
    1.66
    Hopefully
    1.64
     теперь
    1.63
     sẽ
    1.62
     likely
    1.56
    将会
    1.52
    Activations Density 0.057%

    No Known Activations