© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3062
    Prev
    Next
    INDEX
    Explanations

    exceptions, pardons, excuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     反
    0.79
     phản
    0.71
     Reject
    0.70
    強制
    0.70
    反
    0.68
    ukung
    0.67
    的反
    0.66
    拘
    0.64
    しまい
    0.64
    icks
    0.62
    POSITIVE LOGITS
     exemptions
    1.95
     exemption
    1.83
     pardon
    1.81
     exempt
    1.70
     mercy
    1.65
     forgiveness
    1.64
     exempted
    1.63
     pard
    1.61
     forgiving
    1.57
     forgive
    1.54
    Activations Density 0.228%

    No Known Activations