© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73054
    Prev
    Next
    INDEX
    Explanations

    propose, create, organize

    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_10/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
     wahrscheinlich
    -1.44
     beinahe
    -1.35
     northwest
    -1.32
     lediglich
    -1.30
    If
    -1.30
     vermutlich
    -1.27
     trotz
    -1.26
    蓓
    -1.25
    ご了承ください
    -1.25
     speziell
    -1.24
    POSITIVE LOGITS
     helicóptero
    1.50
     теми
    1.40
    izzazione
    1.39
    桖
    1.34
     auta
    1.34
     aktar
    1.31
     experimento
    1.30
    SEGU
    1.29
     fútbol
    1.28
    opic
    1.28
    Activations Density 0.160%

    No Known Activations