© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105215
    Prev
    Next
    INDEX
    Explanations

    Nd:YAG laser, supernatant, gcd

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

    scientific and technical terms from biochemistry, laser technology, and computer science.

    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
    vantaged
    -3.16
     '/')
    -2.88
    贗
    -2.86
    ם
    -2.86
     新款
    -2.61
    leggio
    -2.59
    掮
    -2.59
    tafogo
    -2.55
     aprile
    -2.53
    櫚
    -2.53
    POSITIVE LOGITS
     
    3.75
    2
    3.28
    ing
    3.13
    0
    3.05
    8
    2.97
    5
    2.89
    3
    2.83
    VERY
    2.78
    7
    2.66
     VERY
    2.64
    Activations Density 0.008%

    No Known Activations