© 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. 119878
    Prev
    Next
    INDEX
    Explanations

    cation or cationic

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

    the word "cation" in scientific/chemistry 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
    к
    -2.92
    鱚
    -2.48
    囵
    -2.36
    倌
    -2.34
     observant
    -2.34
    GEBUR
    -2.28
    -2.28
    !"
    -2.27
    ية
    -2.22
    ೣ
    -2.22
    POSITIVE LOGITS
     It
    3.05
    i
    2.80
    をする
    2.73
    
    2.38
    未完
    2.33
     dasarnya
    2.31
    aną
    2.28
    ねぇ
    2.22
    {
    2.20
    chaleco
    2.19
    Activations Density 0.009%

    No Known Activations