© 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. 82480
    Prev
    Next
    INDEX
    Explanations

    transformation and adaptation

    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
     Eyed
    -0.79
    ុ
    -0.79
    loven
    -0.77
     niitä
    -0.76
     HARR
    -0.74
     marinho
    -0.73
    Octo
    -0.72
     vī
    -0.72
    targeting
    -0.71
    ırı
    -0.71
    POSITIVE LOGITS
     transformation
    0.89
     transform
    0.83
     Transform
    0.81
    敌
    0.80
    Transformation
    0.79
    ransition
    0.77
    HasColumnName
    0.77
     Transforming
    0.76
    ⇌
    0.75
    WebVitals
    0.74
    Activations Density 0.020%

    No Known Activations