© 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. 34-GEMMASCOPE-RES-131K
    4. 60800
    Prev
    Next
    INDEX
    Explanations

    creating new instances

    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_34/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
    颖
    -0.89
    𝗩
    -0.88
    ĝis
    -0.85
    wych
    -0.84
     verho
    -0.83
    𝟖
    -0.83
    🧾
    -0.83
     dictionnaire
    -0.82
    რო
    -0.82
    langer
    -0.80
    POSITIVE LOGITS
     new
    8.56
    new
    6.44
     neuen
    4.88
    新的
    4.41
     nuevos
    4.16
     nuevas
    4.16
     neue
    4.09
     nieuwe
    4.09
    新しい
    4.03
     nuovi
    3.95
    Activations Density 0.131%

    No Known Activations