© 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. 60258
    Prev
    Next
    INDEX
    Explanations

    fields of technology

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

    The neuron is tuned to pick out field‐or discipline names ending in the “-ology”/“-technology” suffix.

    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
    ₋
    -1.64
     definitive
    -1.59
    鬭
    -1.48
    饜
    -1.48
    ꜆
    -1.47
    きち
    -1.46
     norvég
    -1.46
     bukti
    -1.45
    小孩
    -1.43
    甶
    -1.41
    POSITIVE LOGITS
    ">
    2.45
    ");
    2.39
    .
    2.30
    0
    2.13
    </sup>
    2.13
     ");
    1.89
    However
    1.81
    </td>
    1.80
    </b>
    1.77
    阄
    1.77
    Activations Density 0.020%

    No Known Activations