© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108231
    Prev
    Next
    INDEX
    Explanations

    digital transformation

    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
    gantian
    -0.86
    高峰
    -0.80
    Mvh
    -0.79
    irer
    -0.79
     however
    -0.77
    RIL
    -0.75
    dists
    -0.75
     Однако
    -0.74
    Stab
    -0.73
    vistas
    -0.73
    POSITIVE LOGITS
     transformation
    2.16
     Transformation
    1.52
     transformations
    1.41
    transformation
    1.38
     transformar
    1.36
     трансформа
    1.34
    Transformation
    1.29
     transforming
    1.29
     transform
    1.20
    转型
    1.20
    Activations Density 0.014%

    No Known Activations