© 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. 111082
    Prev
    Next
    INDEX
    Explanations

    past and a time duration

    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
     other
    -1.18
     current
    -1.12
     currently
    -1.04
     everything
    -1.01
     an
    -0.99
    目前的
    -0.98
    Semoga
    -0.98
    طاء
    -0.98
    ğu
    -0.98
     next
    -0.96
    POSITIVE LOGITS
     few
    3.17
     couple
    2.03
    few
    1.77
     kilka
    1.59
     beberapa
    1.52
     decade
    1.52
     چند
    1.52
    Few
    1.48
     câteva
    1.48
     vài
    1.47
    Activations Density 0.032%

    No Known Activations