© 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. 124114
    Prev
    Next
    INDEX
    Explanations

    code block or license headers

    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
    ’
    -2.50
    i
    -2.47
    es
    -2.30
     teilweise
    -2.27
    ",
    -2.22
    t
    -2.19
    」
    -2.16
     ponen
    -2.14
    </b>
    -2.06
    最大
    -2.06
    POSITIVE LOGITS
    Ꮚ
    2.84
    ܃
    2.81
     sereia
    2.52
     irmã
    2.44
    を買
    2.44
    聍
    2.42
    拶
    2.41
    OUTUBE
    2.38
    ௅
    2.36
    
    2.34
    Activations Density 0.000%

    No Known Activations