© 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. 10-GEMMASCOPE-RES-131K
    7. 7647
    Prev
    Next
    INDEX
    Explanations

    death of someone

    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
    There
    -1.97
    Since
    -1.81
    蕯
    -1.77
    Only
    -1.71
    Surprisingly
    -1.70
    Those
    -1.68
    Some
    -1.64
    You
    -1.60
     descrit
    -1.60
    AdvEx
    -1.59
    POSITIVE LOGITS
    </h1>
    2.38
    ’
    1.88
    ↵
    1.84
    渼
    1.77
    萏
    1.72
    烀
    1.70
    ]$,
    1.68
    眛
    1.66
     certainement
    1.64
    
    1.59
    Activations Density 0.014%

    No Known Activations