© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 12875
    Prev
    Next
    INDEX
    Explanations

    religious laws and moral imperatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    קט
    0.70
    s
    0.63
    स
    0.56
    ब
    0.55
    هم
    0.54
    送り
    0.52
    cdZ
    0.52
    掉
    0.52
     kone
    0.51
    이
    0.51
    POSITIVE LOGITS
     বলিয়াছেন
    0.73
     Commandments
    0.72
    ếu
    0.68
     commandments
    0.66
     বিধি
    0.66
     laws
    0.59
    ujemy
    0.57
     tộc
    0.57
    বিধি
    0.57
    swering
    0.56
    Activations Density 0.026%

    No Known Activations