© 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. 77568
    Prev
    Next
    INDEX
    Explanations

    handwritten character classification

    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
    oose
    -0.75
    rstrip
    -0.74
    tak
    -0.71
     EEA
    -0.71
    TAK
    -0.68
    Nerd
    -0.68
    nesium
    -0.68
     possessed
    -0.67
     экра
    -0.67
     Haag
    -0.66
    POSITIVE LOGITS
     MN
    2.38
    MN
    2.09
    mnist
    2.08
     mn
    1.70
     CIF
    1.69
    Mn
    1.61
     Mn
    1.61
    CIF
    1.48
    cif
    1.35
     cif
    1.33
    Activations Density 0.077%

    No Known Activations