© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66428
    Prev
    Next
    INDEX
    Explanations

    words ending in ing, ed, ton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     manières
    -1.21
     auront
    -1.20
     потря
    -1.14
     lesquels
    -1.13
    وضوع
    -1.11
    Aws
    -1.11
     fédé
    -1.07
     élas
    -1.05
     moderna
    -1.04
     incendie
    -1.04
    POSITIVE LOGITS
    НЫ
    1.28
     سایر
    1.23
    有任何
    1.20
    ath
    1.13
     innych
    1.11
    的其他
    1.11
     iLocal
    1.09
    plusplus
    1.09
    ify
    1.09
    redients
    1.08
    Activations Density 0.121%

    No Known Activations