© 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. 22-GEMMASCOPE-RES-131K
    7. 16001
    Prev
    Next
    INDEX
    Explanations

    autonomous and independent growth

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

    words in a sequence that indicate progression, growth, or spreading of something.

    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_22/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
     ου
    -0.93
     체
    -0.89
     мост
    -0.87
     einverstanden
    -0.83
    guardo
    -0.82
    Награ
    -0.79
    wanne
    -0.79
    すっきり
    -0.78
    積極的に
    -0.77
    requent
    -0.77
    POSITIVE LOGITS
     autonomous
    1.08
     uncontrollable
    1.06
     independent
    1.06
     indépend
    0.96
     independently
    0.96
    ších
    0.95
     beyond
    0.94
    autonomous
    0.90
     indepen
    0.90
    independent
    0.89
    Activations Density 0.033%

    No Known Activations