© 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. 119371
    Prev
    Next
    INDEX
    Explanations

    tired of hearing or watching

    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
    正义
    -0.93
     later
    -0.93
    fgaben
    -0.93
    ină
    -0.91
    完成です
    -0.90
    余裕
    -0.90
     gole
    -0.90
    を行いました
    -0.89
    ingway
    -0.88
    othelioma
    -0.88
    POSITIVE LOGITS
     being
    1.74
     waiting
    1.57
     hearing
    1.44
     always
    1.34
     constantly
    1.32
     постоянно
    1.27
     watching
    1.27
     ständig
    1.24
     trying
    1.23
     seeing
    1.23
    Activations Density 0.025%

    No Known Activations