© 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. 70811
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
     stratég
    -1.69
     expérimentés
    -1.67
     your
    -1.56
    kursi
    -1.55
     sudadera
    -1.52
     escote
    -1.48
     funguje
    -1.47
     boku
    -1.35
     capuz
    -1.34
     comprometido
    -1.34
    POSITIVE LOGITS
    mente
    1.40
     mogą
    1.36
    man
    1.23
    ContentLoaded
    1.22
    ouvoir
    1.20
     beli
    1.20
    。
    1.19
     addSubview
    1.16
    wsze
    1.16
    メイン
    1.15
    Activations Density 0.027%

    No Known Activations