© 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. 100631
    Prev
    Next
    INDEX
    Explanations

    carbon nanotubes abbreviation

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

    acronym "CNT" for carbon nanotubes in 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
     “
    -3.20
    0
    -2.98
    1
    -2.84
    Also
    -2.75
     .”
    -2.75
     Also
    -2.69
     Также
    -2.66
    ”.
    -2.58
    Another
    -2.58
     Roughly
    -2.55
    POSITIVE LOGITS
    ?"
    3.20
    塒
    2.83
    秶
    2.80
    龗
    2.72
     utilizzati
    2.72
    饪
    2.69
     organismes
    2.58
    луйста
    2.56
     fia
    2.48
    ]."
    2.48
    Activations Density 0.001%

    No Known Activations