© 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. 87029
    Prev
    Next
    INDEX
    Explanations

    over-the-top

    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
     catastrophic
    0.43
    )]{
    0.43
    )=
    0.42
    Syn
    0.41
    겐
    0.41
    )</
    0.40
    ั้น
    0.40
     중요한
    0.40
     бизне
    0.39
    Panorama
    0.39
    POSITIVE LOGITS
    ام
    0.64
    不僅
    0.59
     campaigners
    0.58
    ár
    0.55
    抂
    0.55
    étera
    0.55
     escritor
    0.54
    人
    0.54
     nowe
    0.54
     imprime
    0.54
    Activations Density 0.001%

    No Known Activations