© 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. 49481
    Prev
    Next
    INDEX
    Explanations

    rxjs after code constructs

    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
    loads
    -0.81
     cabbage
    -0.68
    ental
    -0.68
    mbe
    -0.68
    zate
    -0.67
    Życiorys
    -0.64
    yat
    -0.64
    johns
    -0.64
     sosyal
    -0.64
    бур
    -0.63
    POSITIVE LOGITS
    oriya
    0.77
    下去
    0.73
    รอบ
    0.68
     footpath
    0.66
     abat
    0.65
     קרי
    0.65
     bottleneck
    0.64
     Batam
    0.64
    それに
    0.63
     TÜV
    0.63
    Activations Density 0.066%

    No Known Activations