© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    programming languages and code snippets

    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
     with
    -1.79
    قامت
    -1.67
    她
    -1.52
    wohner
    -1.51
    Setelah
    -1.48
    提到
    -1.44
     venit
    -1.44
    ztő
    -1.41
    回目
    -1.41
    Ayrıca
    -1.40
    POSITIVE LOGITS
     
    1.97
     infatti
    1.42
     cidad
    1.35
     vocación
    1.34
    顔が
    1.30
     utilizan
    1.30
     оригі
    1.28
     today
    1.28
    柔ら
    1.28
    などに
    1.26
    Activations Density 0.577%

    No Known Activations