© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    immoral requests and atmosphere

    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
    
    1.03
    
    0.99
     ecommerce
    0.98
     kabupaten
    0.98
    
    0.98
     업체
    0.98
     groupby
    0.97
     dataframe
    0.97
    ⛳
    0.95
     onsite
    0.95
    POSITIVE LOGITS
     arrogance
    1.70
     hatred
    1.66
     arrogant
    1.58
     murderous
    1.57
     disgust
    1.53
     disdain
    1.52
     unapolog
    1.50
     merciless
    1.48
     cruel
    1.47
     brutal
    1.47
    Activations Density 0.673%

    No Known Activations