© 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. 110794
    Prev
    Next
    INDEX
    Explanations

    bad followed by negative outcomes

    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
    迨
    -3.11
    茀
    -2.97
    菹
    -2.95
    噲
    -2.80
    
    -2.78
     mentes
    -2.67
    퐿
    -2.66
    阄
    -2.64
    
    -2.64
    hmmm
    -2.61
    POSITIVE LOGITS
    或
    3.19
    s
    3.14
    t
    2.94
    </
    2.41
    a
    2.39
    bo
    2.36
    /
    2.34
     Virtually
    2.34
    .
    2.34
    </b>
    2.30
    Activations Density 0.008%

    No Known Activations