© 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. 74484
    Prev
    Next
    INDEX
    Explanations

    pathway to/toward/for/through/of

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

    The neuron specializes in detecting the word “pathway” (including its capitalized and plural forms) in a document.

    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
    т
    -2.42
    公式サイト
    -2.22
    1
    -2.06
    禤
    -2.06
     was
    -2.05
    銪
    -2.02
    堿
    -1.98
    X
    -1.98
    ツイン
    -1.92
     جمله
    -1.90
    POSITIVE LOGITS
    <td>
    3.08
    你
    2.53
    c
    2.50
     serão
    2.38
     мужчины
    2.28
    นี้
    2.16
     façade
    2.16
    簓
    2.13
    autogui
    2.13
    ized
    2.13
    Activations Density 0.012%

    No Known Activations