© 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. 70243
    Prev
    Next
    INDEX
    Explanations

    what something brings or entails

    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
     is
    -1.19
     are
    -1.00
    有
    -0.94
    是
    -0.94
    thought
    -0.86
    كان
    -0.82
    เป็น
    -0.81
     بوده
    -0.81
    got
    -0.81
    用
    -0.81
    POSITIVE LOGITS
     entails
    1.66
     entail
    1.36
     entailed
    1.33
     represents
    1.18
     brings
    1.05
     delivers
    1.04
     conlle
    1.01
     affords
    1.00
     implies
    0.94
    движи
    0.92
    Activations Density 0.034%

    No Known Activations