© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    biological properties and actions

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

    the word "biological" and related scientific/academic terms.

    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
     verdaderamente
    -2.42
     سواء
    -2.25
     extremadamente
    -2.23
    示意图
    -2.08
     perched
    -1.98
    
    -1.98
     There
    -1.97
     Gouver
    -1.96
     we
    -1.96
     sumamente
    -1.95
    POSITIVE LOGITS
    2
    3.48
    1
    3.02
    3
    2.97
    .
    2.91
    7
    2.63
    ли
    2.42
    })
    2.42
    8
    2.34
    6
    2.28
    by
    2.25
    Activations Density 0.019%

    No Known Activations