© 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. 39382
    Prev
    Next
    INDEX
    Explanations

    poor prognosis, survival, outcomes

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

    The neuron detects the word "poor" when used to describe negative conditions or outcomes.

    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
    ፨
    -2.92
    ⎆
    -2.86
    杙
    -2.73
     самая
    -2.72
    
    -2.72
    唖
    -2.63
    卺
    -2.61
    獰
    -2.61
    ߷
    -2.58
    伥
    -2.55
    POSITIVE LOGITS
    .
    3.39
    s
    3.06
    [
    3.05
    0
    3.02
    2
    2.97
    7
    2.89
    }
    2.83
    8
    2.78
    what
    2.77
    3
    2.75
    Activations Density 0.010%

    No Known Activations