© 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. 9222
    Prev
    Next
    INDEX
    Explanations

    grain and cereals

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

    agricultural terms related to grain and cereals.

    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
    if
    -1.66
    Ọ
    -1.41
     avez
    -1.36
    ăzi
    -1.33
    łec
    -1.32
    ıt
    -1.32
     என்ப
    -1.32
    PA
    -1.29
     existir
    -1.27
    }
    
    -1.27
    POSITIVE LOGITS
    solicited
    1.70
     любой
    1.33
    していた
    1.31
     be
    1.30
    только
    1.29
    凩
    1.25
    !)
    1.23
     grain
    1.23
    菝
    1.22
     visitó
    1.21
    Activations Density 0.031%

    No Known Activations