© 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. 48523
    Prev
    Next
    INDEX
    Explanations

    biological effector protein or function

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

    The neuron detects the scientific term "effector" in biological, molecular, or neural 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
    u
    -2.92
    </strong>
    -2.59
    </h3>
    -2.25
    on
    -2.17
    …”
    -2.14
     Then
    -2.13
     групп
    -2.11
    ла
    -2.08
    …
    -2.06
    ….”
    -2.03
    POSITIVE LOGITS
    硨
    2.66
    ࿙
    2.55
    垆
    2.53
    鲎
    2.48
    拮
    2.48
    '
    2.47
     帅气
    2.39
    炻
    2.34
    ！！”
    2.30
    氖
    2.30
    Activations Density 0.051%

    No Known Activations