© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4538
    Prev
    Next
    INDEX
    Explanations

    refusing harmful content, suggesting help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     considering
    0.78
     wondering
    0.76
     personnes
    0.74
    ̑
    0.74
     réserv
    0.73
     wishing
    0.72
    enciales
    0.72
     priprav
    0.71
     recommending
    0.70
    :",
    0.70
    POSITIVE LOGITS
    但是
    0.62
     However
    0.61
    əs
    0.59
     Let
    0.59
     Yes
    0.58
     Well
    0.57
    Yes
    0.57
     ইতিহাসে
    0.57
     murdered
    0.57
    かつ
    0.56
    Activations Density 0.272%

    No Known Activations