© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13083
    Prev
    Next
    INDEX
    Explanations

    DENVER COLORADO

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

    Confluence, DevExtreme, Streamlit

    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
    -
    0.36
    _
    0.34
    ҳои
    0.31
     produkter
    0.31
    ⁺
    0.31
    🈺
    0.30
    джи
    0.30
    шава
    0.30
    𝘼
    0.29
    -$\
    0.29
    POSITIVE LOGITS
     Millionen
    0.28
     MEC
    0.28
     Egipto
    0.27
     Madrid
    0.27
     Kanada
    0.27
     distraught
    0.27
     Verify
    0.26
    <unused1748>
    0.26
     Manchester
    0.26
     बड़ा
    0.25
    Activations Density 0.120%

    No Known Activations