© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    abstract qualities ending in ness

    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
    When
    -3.31
    🎉
    -3.17
    Despite
    -3.13
    🥳
    -3.09
    Making
    -3.03
    Getting
    -3.00
    Putting
    -2.86
    😆
    -2.83
     blatantly
    -2.81
    導致
    -2.80
    POSITIVE LOGITS
    
    3.14
     of
    3.13
    .
    2.95
    
    2.88
    斟
    2.88
     REALLY
    2.83
     VERY
    2.80
     exceptionally
    2.78
    ☫
    2.77
     sublime
    2.75
    Activations Density 0.021%

    No Known Activations