© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7359
    Prev
    Next
    INDEX
    Explanations

    addressing refusals or sensitive topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     whopping
    0.76
     begged
    0.76
     deliciously
    0.75
    !)
    0.75
     stupid
    0.75
    !
    0.73
     sexy
    0.73
     damning
    0.70
    ！
    0.70
     damned
    0.70
    POSITIVE LOGITS
     Unfortunately
    0.90
     unfortunately
    0.86
     сожалению
    0.82
     concerns
    0.82
    Unfortunately
    0.79
     misunderstand
    0.79
     misunder
    0.78
     বেশকিছু
    0.73
     inappropriate
    0.72
     incorrect
    0.71
    Activations Density 1.128%

    No Known Activations