© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108639
    Prev
    Next
    INDEX
    Explanations

    biological and social axes

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

    text in HTML/code comments and auto-generated code sections.

    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
    waits
    -0.68
    tiff
    -0.67
     controversy
    -0.67
     equivo
    -0.66
    Tradu
    -0.66
    agna
    -0.66
    LPS
    -0.65
    
    -0.64
    ütz
    -0.64
    removeChild
    -0.64
    POSITIVE LOGITS
     pumping
    0.77
    美子
    0.74
    ULTURA
    0.71
     Pumps
    0.70
     nexus
    0.69
     Pumping
    0.69
     pyp
    0.68
     Racial
    0.66
    browse
    0.66
    パートナー
    0.66
    Activations Density 0.066%

    No Known Activations