© 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. 10-GEMMASCOPE-RES-131K
    4. 69477
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
     then
    -1.57
     now
    -1.16
     and
    -1.16
     sabiduría
    -1.10
     until
    -1.06
    vereins
    -1.06
    更何况
    -1.06
    我现在
    -1.05
     tatt
    -1.03
     Sénégal
    -1.01
    POSITIVE LOGITS
    covite
    1.24
    .),
    1.23
     sekitar
    1.21
    astify
    1.20
    (!__
    1.19
     auttaa
    1.19
     "),
    1.16
    ຣ
    1.15
    だめ
    1.15
    ことがあります
    1.15
    Activations Density 0.181%

    No Known Activations