© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 622
    Prev
    Next
    INDEX
    Explanations

    table rows and headers

    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
    าล
    0.39
    乱流
    0.36
    Coref
    0.36
    itipi
    0.36
    廨
    0.35
     breech
    0.34
     motivic
    0.34
     voy
    0.34
    ന്വേഷ
    0.33
    ั้น
    0.33
    POSITIVE LOGITS
    |
    0.51
    TableRow
    0.38
     |
    0.38
    |-\
    0.37
     Sh
    0.37
    |-
    0.37
    表
    0.36
     Magn
    0.35
    |$
    0.35
    |)
    0.34
    Activations Density 0.003%

    No Known Activations