© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15356
    Prev
    Next
    INDEX
    Explanations

    lifespan, Pb, Php

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

    This neuron detects references to "lifespan" and the chemical element "Pb" (lead).

    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
     nourished
    -3.16
    ☫
    -3.08
    鼙
    -2.94
    ه
    -2.88
    “
    -2.66
    o
    -2.66
    ፨
    -2.63
    戬
    -2.58
    鋲
    -2.56
    ⬈
    -2.53
    POSITIVE LOGITS
    是
    3.09
    可以
    2.69
    März
    2.44
     parlar
    2.41
    のである
    2.39
    蹋
    2.39
     estekak
    2.34
     сделал
    2.33
    genodigd
    2.31
    ми
    2.30
    Activations Density 0.008%

    No Known Activations