© 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. 83137
    Prev
    Next
    INDEX
    Explanations

    continuation and extension

    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
     будущего
    -1.04
    eventually
    -0.98
    最後に
    -0.98
     nikdy
    -0.93
    remains
    -0.90
     Encourage
    -0.90
    became
    -0.90
    梱
    -0.88
     объяви
    -0.88
    becoming
    -0.88
    POSITIVE LOGITS
     continuation
    3.55
     Continuation
    2.80
     continuing
    2.80
    continuation
    2.70
     continue
    2.63
     continued
    2.59
     продол
    2.56
    Continuing
    2.55
    延续
    2.52
    继续
    2.50
    Activations Density 0.144%

    No Known Activations