© 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. 22-GEMMASCOPE-RES-131K
    4. 74907
    Prev
    Next
    INDEX
    Explanations

    lack of oxygen leading to death

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

    words and concepts related to suffocation, drowning, and oxygen deprivation.

    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_22/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
     was
    -1.52
     中身
    -1.52
    al
    -1.43
     niż
    -1.41
     メニュー
    -1.33
    能在
    -1.33
    튿
    -1.30
    
    -1.28
     Forscher
    -1.27
     Zentrum
    -1.26
    POSITIVE LOGITS
    },
    1.41
    ',
    1.41
    ionales
    1.39
    }
    1.38
     nové
    1.38
     drowning
    1.37
     венти
    1.36
    ↵
    1.36
     "",
    1.34
     suffoc
    1.34
    Activations Density 0.047%

    No Known Activations