© 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. 34-GEMMASCOPE-RES-131K
    4. 38060
    Prev
    Next
    INDEX
    Explanations

    legal judgments affirmed

    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
    ólicas
    -0.79
    пры
    -0.75
     banana
    -0.74
    паль
    -0.71
     juzg
    -0.71
    香蕉
    -0.71
     Qatar
    -0.71
    inely
    -0.70
     NSError
    -0.70
    banana
    -0.69
    POSITIVE LOGITS
     affirmed
    3.02
     upheld
    2.78
     affirm
    2.63
     affirming
    2.58
     uphold
    2.58
     affirmation
    2.34
     upholding
    2.25
     Affirm
    2.22
    affirm
    2.20
    Affirmed
    2.20
    Activations Density 0.273%

    No Known Activations