© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 187
    Prev
    Next
    INDEX
    Explanations

    locations and infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite

    plants produce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x0D>
    0.22
     furent
    0.22
     đây
    0.21
     তেমনই
    0.20
    などを
    0.19
     riguard
    0.19
     помогут
    0.19
     ထ
    0.19
    annotation
    0.19
     quién
    0.19
    POSITIVE LOGITS
    ’
    0.28
     memiliki
    0.23
     overall
    0.21
     lacks
    0.21
    wide
    0.21
    整体
    0.21
     punya
    0.21
    面临
    0.20
    творе
    0.20
     находиться
    0.19
    Activations Density 1.523%

    No Known Activations