© 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. 32891
    Prev
    Next
    INDEX
    Explanations

    starting to post or view

    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
     continuing
    -1.34
    continuing
    -1.23
     продолжает
    -1.21
     jederzeit
    -1.19
    继续
    -1.19
    Continuing
    -1.17
     continue
    -1.15
    最後まで
    -1.12
     продъл
    -1.11
    これからも
    -1.09
    POSITIVE LOGITS
     seriously
    1.67
    本格
    1.45
     serious
    1.39
     more
    1.34
     earnest
    1.33
     zaczą
    1.30
     begins
    1.27
     again
    1.21
     starts
    1.20
     really
    1.17
    Activations Density 0.049%

    No Known Activations