© 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. 45449
    Prev
    Next
    INDEX
    Explanations

    affects, afflictions, affair

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

    the term "aff" in different contexts, especially in "Affero" from software licenses and other biological/medical 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_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
    佼
    -2.45
    もあって
    -2.41
     advertencia
    -2.36
    zdroj
    -2.33
    UCIÓN
    -2.33
    которые
    -2.33
    
    -2.28
     postulated
    -2.23
    でもない
    -2.23
     Перейти
    -2.23
    POSITIVE LOGITS
    s
    4.38
    O
    3.30
    “
    3.16
    h
    3.06
    4
    2.92
    a
    2.88
    6
    2.86
    5
    2.81
     --
    2.70
    name
    2.66
    Activations Density 0.002%

    No Known Activations