© 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. 108512
    Prev
    Next
    INDEX
    Explanations

    admitting wrongdoing or guilt

    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
     reassurance
    -1.09
     assurance
    -1.04
     reported
    -1.04
     anybody
    -1.03
     assured
    -1.00
    ņem
    -0.99
     biztos
    -0.98
     scheint
    -0.98
    ch
    -0.96
    ه‌ای
    -0.95
    POSITIVE LOGITS
     to
    1.78
     defeat
    1.55
    nerability
    1.19
     culpa
    1.19
     Kristus
    1.13
     admits
    1.11
    candid
    1.09
     wrongdoing
    1.09
     admiti
    1.02
     romantis
    1.01
    Activations Density 0.012%

    No Known Activations