© 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. 34-GEMMASCOPE-RES-131K
    7. 59123
    Prev
    Next
    INDEX
    Explanations

    cinnamon, Mint, City

    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_34/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
    nhof
    -0.73
     comprehen
    -0.72
    userinfo
    -0.70
     Sovereign
    -0.69
    compress
    -0.69
    entral
    -0.68
    传递
    -0.67
     Margot
    -0.67
    collectionView
    -0.67
    istes
    -0.67
    POSITIVE LOGITS
     cinnamon
    3.67
     Cinnamon
    3.00
    Cinnamon
    2.67
    cinnamon
    2.61
     cin
    2.16
     canela
    2.02
    Cin
    1.96
     Cin
    1.94
    CIN
    1.63
     CIN
    1.63
    Activations Density 0.046%

    No Known Activations