© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77665
    Prev
    Next
    INDEX
    Explanations

    bitter and sweet

    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
     coloridos
    -0.93
    
    -0.88
    fions
    -0.83
     mê
    -0.81
     bib
    -0.81
    ueves
    -0.81
    共产
    -0.80
     ц
    -0.80
    ̱
    -0.80
    entle
    -0.79
    POSITIVE LOGITS
     sweet
    1.48
    Sweet
    1.45
     Sweet
    1.39
    weet
    1.38
    sweet
    1.35
     sweeter
    1.00
    SWEET
    0.99
     taste
    0.97
    Bitter
    0.91
     bitter
    0.90
    Activations Density 0.006%

    No Known Activations