© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115495
    Prev
    Next
    INDEX
    Explanations

    assisted death

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

    technical or scientific text with a focus on data, measurements, and computational terminology.

    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_34/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
     reissue
    -0.80
     tweaked
    -0.73
     سے
    -0.71
    ANGEL
    -0.68
    woosh
    -0.68
     quoti
    -0.68
    HALT
    -0.67
    ALY
    -0.67
     Tomaten
    -0.67
    yaç
    -0.66
    POSITIVE LOGITS
     event
    2.06
     events
    1.89
    event
    1.65
     Event
    1.59
     Events
    1.57
    Event
    1.52
    Events
    1.45
    events
    1.45
    イベント
    1.41
     EVENTS
    1.34
    Activations Density 0.016%

    No Known Activations