© 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. 22-GEMMASCOPE-RES-131K
    7. 27484
    Prev
    Next
    INDEX
    Explanations

    cause of personal thoughts

    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_22/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
     saveurs
    -0.94
    nek
    -0.94
    qr
    -0.93
    van
    -0.91
    vans
    -0.90
     perro
    -0.88
    zony
    -0.88
    abril
    -0.88
    LEGGI
    -0.87
     Erkrankungen
    -0.86
    POSITIVE LOGITS
     his
    1.84
     he
    1.35
     его
    1.21
     njego
    1.13
     himself
    1.06
     suoi
    1.04
     their
    1.03
     jego
    1.02
     yaptığı
    0.95
     그의
    0.94
    Activations Density 0.052%

    No Known Activations