© 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. 31-GEMMASCOPE-2-RES-262K
    7. 51610
    Prev
    Next
    INDEX
    Explanations

    discussing limitations

    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_31_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
    smoothed
    0.49
    ской
    0.48
    тков
    0.46
    MaxSize
    0.46
    ков
    0.45
    зия
    0.45
    шей
    0.44
    肇
    0.44
    内
    0.42
    бе
    0.42
    POSITIVE LOGITS
     étaient
    0.54
     mistura
    0.53
     campuran
    0.52
     estavam
    0.51
     perguntas
    0.50
     Algeria
    0.49
    磔
    0.49
     leuke
    0.49
     organize
    0.49
     solução
    0.49
    Activations Density 0.001%

    No Known Activations