© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58351
    Prev
    Next
    INDEX
    Explanations

    mutagenesis, Bhaskar, mAh

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

    technical terms related to genetics, biochemistry, or scientific research, particularly focusing on mutations and measurements.

    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
     superfí
    -2.53
    髫
    -2.52
    珖
    -2.50
    
    -2.48
    劄
    -2.48
     フィルム
    -2.47
    㩒
    -2.47
     geografia
    -2.47
    瞜
    -2.42
    銠
    -2.34
    POSITIVE LOGITS
    O
    3.72
    M
    3.38
    8
    3.09
    \
    2.83
    3
    2.81
    F
    2.81
    it
    2.73
    -
    2.67
    L
    2.66
    For
    2.64
    Activations Density 0.005%

    No Known Activations