© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15106
    Prev
    Next
    INDEX
    Explanations

    ease or difficulty

    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_10/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
    罍
    -1.78
     restant
    -1.74
    蟶
    -1.70
    僦
    -1.68
    urcht
    -1.66
    medriver
    -1.66
    螄
    -1.63
     representado
    -1.62
     abundante
    -1.62
     conectado
    -1.62
    POSITIVE LOGITS
    0
    2.22
     for
    2.05
     of
    1.83
    了一
    1.69
     não
    1.67
    p
    1.59
    f
    1.56
     Of
    1.55
     understands
    1.53
    8
    1.51
    Activations Density 0.012%

    No Known Activations