© 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. 10-GEMMASCOPE-RES-131K
    7. 85905
    Prev
    Next
    INDEX
    Explanations

    mime, mimetic, peptidomimetic

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

    references to "mimetic" terms and MIME file types in technical or scientific 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_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
    ↵↵
    -3.42
     ‘
    -3.41
    ‘
    -2.95
    .”
    -2.91
    ’,
    -2.73
     \
    -2.70
    -2.64
     {
    -2.59
    ());
    -2.50
    }$.
    -2.50
    POSITIVE LOGITS
     VIET
    2.53
    Mereka
    2.52
     parfü
    2.45
    囖
    2.38
    鯔
    2.38
    芣
    2.38
    ︐
    2.34
     rangs
    2.33
     qualifi
    2.30
    
    2.28
    Activations Density 0.008%

    No Known Activations