© 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. 10-GEMMASCOPE-RES-131K
    4. 72878
    Prev
    Next
    INDEX
    Explanations

    Beck depression, lymph nodes

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

    The neuron identifies names containing "Beck" or forms of "Beck" in different contexts (like Beck Depression Inventory, Glenn Beck, or surnames like Beckner).

    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
    残酷
    -2.75
    ization
    -2.73
    </h3>
    -2.50
    
    -2.48
    </strong>
    -2.39
    鹇
    -2.39
    秫
    -2.38
    蛧
    -2.38
    ਲ਼
    -2.36
    镂
    -2.30
    POSITIVE LOGITS
     eminently
    2.61
    </td>
    2.44
    </b>
    2.42
    [
    2.38
    𓇼
    2.34
     rattled
    2.30
     szczeg
    2.25
    «
    2.23
    ]
    2.22
    ↵
    2.19
    Activations Density 0.008%

    No Known Activations