© 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. 22-GEMMASCOPE-RES-131K
    7. 28437
    Prev
    Next
    INDEX
    Explanations

    multi-lingual classification

    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
    providedIn
    -1.34
     EconPapers
    -1.24
    arschu
    -1.18
    underland
    -1.14
    ところに
    -1.14
     descuento
    -1.13
     dotyczą
    -1.12
    にあった
    -1.09
     demora
    -1.09
    感じです
    -1.08
    POSITIVE LOGITS
    所以在
    1.19
    などが
    1.14
    Более
    1.08
     انگلیسی
    1.03
     國際
    0.97
     etc
    0.97
    不断的
    0.93
    瞟
    0.92
    忐
    0.92
     incontro
    0.91
    Activations Density 0.137%

    No Known Activations