© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    absence of worry or problems

    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
    níků
    -0.97
     bazı
    -0.96
    gunaan
    -0.95
     매우
    -0.93
    Tum
    -0.93
     ralenti
    -0.92
     feasting
    -0.91
    alisis
    -0.90
    Wishlist
    -0.90
     دهه
    -0.90
    POSITIVE LOGITS
     worry
    1.67
     worries
    1.65
     any
    1.43
     worrying
    1.31
     worried
    1.25
    担心
    1.24
     žiad
    1.16
     accidental
    1.11
     added
    1.10
     concerns
    1.09
    Activations Density 0.033%

    No Known Activations