© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20229
    Prev
    Next
    INDEX
    Explanations

    death of someone/something

    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
    ౭
    -1.65
     virtuel
    -1.59
     diverses
    -1.57
    THO
    -1.55
     ;
    -1.52
     frapp
    -1.48
    ໋
    -1.47
     batterie
    -1.46
     prostitu
    -1.46
     broderie
    -1.45
    POSITIVE LOGITS
     and
    1.59
     at
    1.52
     With
    1.48
     two
    1.47
     through
    1.43
     on
    1.38
     or
    1.37
     by
    1.34
    .
    1.34
     chose
    1.27
    Activations Density 0.033%

    No Known Activations