© 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. 10559
    Prev
    Next
    INDEX
    Explanations

    terminal illness, dying, and end-stage diseases

    np_acts-logits-general · gemini-2.5-flash-lite

    references to terminal illness and end-stage disease.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    琬
    -1.47
     sierp
    -1.45
     referentes
    -1.38
    barry
    -1.38
     και
    -1.37
    哢
    -1.37
     proposes
    -1.35
     які
    -1.33
    lievo
    -1.32
    卣
    -1.32
    POSITIVE LOGITS
    1
    1.47
    3
    1.41
    9
    1.39
    4
    1.38
    5
    1.27
     how
    1.27
     pekan
    1.26
    2
    1.25
    how
    1.24
    frac
    1.23
    Activations Density 0.058%

    No Known Activations