© 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. 71981
    Prev
    Next
    INDEX
    Explanations

    life events or personal situations

    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
     transporta
    -0.93
     statunit
    -0.92
    G
    -0.92
     diete
    -0.89
     futu
    -0.88
     даже
    -0.88
    al
    -0.87
     quienes
    -0.85
     forefathers
    -0.84
    août
    -0.82
    POSITIVE LOGITS
     his
    2.36
     himself
    2.06
    himself
    1.59
     خودش
    1.13
     нього
    0.99
     seiner
    0.98
     yaptığı
    0.98
     kühl
    0.97
     réessayer
    0.97
     своей
    0.96
    Activations Density 0.077%

    No Known Activations