© 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. 21826
    Prev
    Next
    INDEX
    Explanations

    mathematical variables in expressions

    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
    頃は
    -1.43
     meningkat
    -1.43
    mascara
    -1.33
    驁
    -1.30
    前来
    -1.30
    嵛
    -1.29
    蟜
    -1.28
    rrh
    -1.28
     no
    -1.27
     terwijl
    -1.26
    POSITIVE LOGITS
    鲼
    1.57
    </h5>
    1.48
     歳
    1.46
    I
    1.43
     玩具
    1.43
     definitivamente
    1.41
    lings
    1.38
    知名
    1.37
    ítani
    1.37
    发表于
    1.36
    Activations Density 0.037%

    No Known Activations