© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8091
    Prev
    Next
    INDEX
    Explanations

    cancer/testis, circadian time, childhood trauma

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

    The neuron identifies abbreviations and acronyms beginning with "CT", particularly in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly selective for the uppercase token “CT” (often appearing as part of abbreviations or acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     taurus
    -2.52
    ે
    -2.31
     بودند
    -2.20
    我們
    -2.16
    anyahu
    -2.09
    沒有
    -2.06
    現在の
    -2.02
    ום
    -2.02
    Где
    -2.00
    ありますが
    -1.98
    POSITIVE LOGITS
    ’
    3.53
    ]
    3.19
     ‘
    2.77
    ’,
    2.72
     notre
    2.69
     }
    2.66
     amazing
    2.64
    再多
    2.55
    y
    2.53
     wonderful
    2.47
    Activations Density 0.019%

    No Known Activations