© 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. 120063
    Prev
    Next
    INDEX
    Explanations

    gk, gkmc, g.k. initials

    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_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
    ࿚
    -2.70
    嘁
    -2.59
    。“
    -2.39
     красота
    -2.27
    骓
    -2.25
    ஂ
    -2.22
    磲
    -2.20
    鲀
    -2.20
    できる
    -2.16
    芣
    -2.13
    POSITIVE LOGITS
    '
    2.45
    n
    2.34
    去
    2.20
    可以
    2.17
    ℟
    2.11
    2.09
    cuba
    2.09
     igr
    2.08
    *
    2.08
     GK
    2.05
    Activations Density 0.006%

    No Known Activations