© 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. 22-GEMMASCOPE-RES-131K
    7. 27405
    Prev
    Next
    INDEX
    Explanations

    brain health or rhabdomyolysis

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

    numerical values in various contexts, particularly dates, version numbers, and file paths.

    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
     staunch
    -1.05
    warted
    -1.01
    𓆟
    -0.99
     demora
    -0.98
     reduces
    -0.98
     steadfast
    -0.97
    municipi
    -0.97
     northern
    -0.96
     tiras
    -0.94
     superbly
    -0.94
    POSITIVE LOGITS
     trois
    0.92
    Према
    0.88
     itt
    0.87
    Bjs
    0.85
    Standard
    0.84
    ↵↵
    0.84
      
    0.84
    sfw
    0.83
    now
    0.82
    跟我
    0.82
    Activations Density 0.025%

    No Known Activations