© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111285
    Prev
    Next
    INDEX
    Explanations

    sewage treatment, HPLC analysis

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

    technical terms like "sewage" and "HPLC" in scientific or technical contexts.

    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
    {
    -3.27
    
    -2.63
    
    -2.63
    ’
    -2.55
    .’
    -2.45
    できる
    -2.38
    }
    -2.38
    辚
    -2.25
    ,[
    -2.23
    ࿚
    -2.23
    POSITIVE LOGITS
    各样的
    2.66
     OGSÅ
    2.39
    无比
    2.31
    瞬间
    2.20
    屺
    2.19
     دیواری
    2.09
    刳
    2.05
     tenets
    2.03
    神情
    1.98
    𝗴
    1.98
    Activations Density 0.012%

    No Known Activations