© 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. 14729
    Prev
    Next
    INDEX
    Explanations

    movie night, dog running, university president

    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
     Städ
    0.35
    statistik
    0.35
     सुचेता
    0.34
    珏
    0.33
    螈
    0.32
     isEqualToString
    0.32
     চলতি
    0.32
    荩
    0.32
    洺
    0.32
     Statistik
    0.31
    POSITIVE LOGITS
    0.40
     جهاز
    0.39
     jednu
    0.37
     telefone
    0.37
     لكن
    0.36
    arr
    0.35
     جارہ
    0.35
     خلي
    0.35
    :
    0.35
     but
    0.34
    Activations Density 0.092%

    No Known Activations