© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63391
    Prev
    Next
    INDEX
    Explanations

    people with specific conditions

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

    prepositions (like "for", "with", "of", "to") that introduce relationships between entities, particularly in medical or service 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_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
     водитель
    -0.99
     examiners
    -0.87
    buyer
    -0.85
    geordnet
    -0.84
     aparcamiento
    -0.84
     exhibitors
    -0.83
    subplot
    -0.82
    writers
    -0.82
     пользователь
    -0.81
    player
    -0.81
    POSITIVE LOGITS
     disabled
    2.89
     elderly
    2.33
     homeless
    2.30
     unemployed
    2.22
     injured
    2.19
     obese
    2.19
     pregnant
    2.17
     sick
    2.14
     wounded
    2.05
     handicapped
    2.02
    Activations Density 0.304%

    No Known Activations