© 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. 127421
    Prev
    Next
    INDEX
    Explanations

    declarations and annotations

    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
     المزيد
    -1.63
     című
    -1.58
    žena
    -1.45
    heureux
    -1.41
    すぎる
    -1.41
    скую
    -1.38
    ＾
    -1.38
    обзор
    -1.37
    めに
    -1.35
    rimiento
    -1.35
    POSITIVE LOGITS
     also
    2.11
    also
    1.95
     juga
    1.73
     también
    1.73
     cũng
    1.72
     additionally
    1.69
     Auffassung
    1.66
     it
    1.65
     גם
    1.65
    canakan
    1.63
    Activations Density 0.006%

    No Known Activations