© 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. 65271
    Prev
    Next
    INDEX
    Explanations

    molecular scientific analysis

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

    The neuron activates for the word "molecular" when used in scientific contexts, particularly in relation to biology or genetic research.

    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
     emozioni
    -2.38
    嘰
    -2.30
    鼉
    -2.22
    珍珠
    -2.22
    一個
    -2.09
     качество
    -2.06
    多かった
    -2.06
    缡
    -2.00
    主に
    -1.98
    warnai
    -1.97
    POSITIVE LOGITS
    婓
    3.03
    茀
    2.88
    弍
    2.86
    酲
    2.55
     și
    2.52
    衕
    2.52
    𖥧
    2.47
    ']
    2.45
    亊
    2.38
    </td>
    2.34
    Activations Density 0.019%

    No Known Activations