© 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. 34-GEMMASCOPE-RES-131K
    7. 45385
    Prev
    Next
    INDEX
    Explanations

    future possibilities and predictions

    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
    そろそろ
    -1.15
    clearly
    -1.00
    generally
    -1.00
    確かに
    -1.00
    obviously
    -0.96
    diğ
    -0.96
     >",
    -0.96
    毁灭
    -0.95
    これ
    -0.94
     lately
    -0.94
    POSITIVE LOGITS
     possibly
    2.03
     probably
    1.93
     maybe
    1.77
     likely
    1.68
     promise
    1.66
     mark
    1.66
     predicted
    1.63
     hopefully
    1.63
     unless
    1.59
     guaranteed
    1.58
    Activations Density 0.034%

    No Known Activations