© 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. 34-GEMMASCOPE-RES-131K
    7. 57876
    Prev
    Next
    INDEX
    Explanations

    Madras, Madin, Madhukar, Madurai

    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
     če
    -0.84
    ļi
    -0.80
    pses
    -0.77
     placé
    -0.76
    ceb
    -0.75
    prehension
    -0.73
     froide
    -0.73
    replaceable
    -0.73
     élevés
    -0.71
    focused
    -0.71
    POSITIVE LOGITS
     courtesy
    0.87
     regelmäßig
    0.74
    brities
    0.71
    WindowListener
    0.70
     biggest
    0.67
     getNum
    0.67
     Massimo
    0.66
    あえず
    0.66
     рі
    0.65
     hurts
    0.65
    Activations Density 0.026%

    No Known Activations