© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    wrought iron, stones, concrete

    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
    O
    -2.14
    呿
    -2.11
     doloroso
    -2.09
     diki
    -2.06
    which
    -2.02
     nogle
    -1.99
    
    -1.93
    ﮦ
    -1.93
    衚
    -1.90
    割と
    -1.89
    POSITIVE LOGITS
     and
    2.44
     in
    2.03
     使っ
    1.78
    朱印
    1.74
     at
    1.65
    ！！”
    1.55
    .''
    1.53
    棘
    1.50
    ？！”
    1.48
    💎
    1.47
    Activations Density 0.011%

    No Known Activations