© 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. 104893
    Prev
    Next
    INDEX
    Explanations

    valence-related chemical and physical terms

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

    chemistry-related terms referring to valence, especially "valent" in "monovalent", "polyvalent", and similar compounds.

    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
     You
    -2.38
    ៦
    -2.34
    .
    -2.31
     ehemalige
    -2.19
     großes
    -2.17
    櫺
    -2.17
     schönes
    -2.08
    pulseira
    -2.08
     itſelf
    -2.03
     ganzes
    -2.02
    POSITIVE LOGITS
    2
    2.97
    ⚋
    2.88
    ～　
    2.55
    ꔛ
    2.48
    </sup>
    2.20
    A
    2.19
    ごめんなさい
    2.17
    の高い
    2.17
    𓐍
    2.11
    鸰
    2.11
    Activations Density 0.006%

    No Known Activations