© 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. 102213
    Prev
    Next
    INDEX
    Explanations

    System. Windows, Cardio, Hey, Introduction

    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
     konusu
    -1.78
     sabias
    -1.73
     inspiradoras
    -1.69
     seçenek
    -1.57
     myös
    -1.55
     seguras
    -1.54
     preciosas
    -1.54
     explicado
    -1.54
     unsuccessful
    -1.52
    せよ
    -1.49
    POSITIVE LOGITS
     menti
    1.65
    }_{
    1.52
    Ⅵ
    1.48
     manj
    1.48
     رابطه
    1.48
    ра
    1.44
     altezza
    1.40
     kater
    1.39
    ulence
    1.38
    ⢪
    1.38
    Activations Density 0.000%

    No Known Activations