© 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. 21917
    Prev
    Next
    INDEX
    Explanations

    sports positions and areas

    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
    幛
    -1.41
    Actually
    -1.37
    もちろん
    -1.37
    罍
    -1.36
     that
    -1.32
     loob
    -1.30
    敺
    -1.27
    actually
    -1.26
    。
    
    -1.26
     唯美
    -1.24
    POSITIVE LOGITS
     if
    1.42
     akkor
    1.41
    \
    1.41
    itoral
    1.39
     of
    1.33
    }$,
    1.29
     Zjednoc
    1.28
    脯
    1.21
    ."
    1.21
    andeep
    1.20
    Activations Density 0.011%

    No Known Activations