© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111023
    Prev
    Next
    INDEX
    Explanations

    cattle breeds and traits

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

    terms related to animal agriculture and livestock breeding.

    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_34/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
     Ingo
    -0.75
    ffin
    -0.74
    singular
    -0.72
    軛
    -0.72
     Gallo
    -0.68
    下载附件
    -0.68
     markets
    -0.67
    Regions
    -0.65
     cantor
    -0.65
    マーケット
    -0.64
    POSITIVE LOGITS
     semen
    1.13
     genomic
    0.99
     flushed
    0.88
     koti
    0.87
    噛
    0.86
    semen
    0.86
    ఎ
    0.85
    idential
    0.85
     genetics
    0.83
     embry
    0.82
    Activations Density 0.007%

    No Known Activations