© 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. 10-GEMMASCOPE-RES-131K
    7. 120014
    Prev
    Next
    INDEX
    Explanations

    trail running, riding, and journeys

    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
    }
    -2.52
     другими
    -2.28
    Ꝑ
    -2.27
     se
    -2.25
     glaring
    -2.22
    囪
    -2.20
     troublesome
    -2.17
    櫪
    -2.14
    
    -2.14
    
    -2.14
    POSITIVE LOGITS
    婓
    2.89
     richten
    2.50
    vités
    2.45
     měla
    2.45
    кий
    2.28
     bedienen
    2.19
     yf
    2.19
    乆
    2.19
     spiegel
    2.17
    ون
    2.16
    Activations Density 0.005%

    No Known Activations