© 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. 34-GEMMASCOPE-RES-131K
    7. 111110
    Prev
    Next
    INDEX
    Explanations

    originally

    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
    حال
    -0.83
    culado
    -0.81
    przed
    -0.77
    zdjęcie
    -0.74
    ){$
    -0.73
    𝒜
    -0.73
    Zurück
    -0.71
    brochen
    -0.71
    spel
    -0.70
    出一个
    -0.68
    POSITIVE LOGITS
    Originally
    6.63
     originally
    5.81
     Originally
    4.78
     originalmente
    3.81
    originally
    3.78
     ursprünglich
    3.16
     original
    2.88
     oorspron
    2.48
    原本
    2.45
    本来
    2.34
    Activations Density 0.135%

    No Known Activations