© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31671
    Prev
    Next
    INDEX
    Explanations

    foreign words and names

    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_40_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
    निश्ड
    0.33
     LOTRAchievement
    0.32
     داله
    0.30
     prostagland
    0.29
    <unused0>
    0.28
    <unused2110>
    0.28
    <unused2221>
    0.28
     tetragonal
    0.27
    婧
    0.27
    <unused2137>
    0.26
    POSITIVE LOGITS
    op
    0.41
    -
    0.41
    ot
    0.38
    re
    0.37
    ag
    0.37
    ase
    0.36
    id
    0.36
    un
    0.36
    ad
    0.36
    arr
    0.36
    Activations Density 0.011%

    No Known Activations