© 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-262K
    7. 1326
    Prev
    Next
    INDEX
    Explanations

    effectiveness and quality

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

    efficiency, creativity, quality

    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_262k_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
     cosidd
    0.21
     linemen
    0.20
     Americans
    0.20
     monies
    0.20
     America
    0.20
    ”
    0.19
     (
    0.19
     prostitutes
    0.19
     luncheon
    0.19
     үч
    0.18
    POSITIVE LOGITS
    💼
    0.25
     enthr
    0.23
     י
    0.22
     captivating
    0.22
     प्रभावशाली
    0.21
     Ubuy
    0.20
     beeindruck
    0.20
    🎊
    0.20
    <0xCD>
    0.20
     ע
    0.20
    Activations Density 0.044%

    No Known Activations