© 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. 11267
    Prev
    Next
    INDEX
    Explanations

    Thanks a lot

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

    *

    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
     বেশকিছু
    0.47
     \
    0.46
    occup
    0.45
    IN
    0.44
    do
    0.44
    ave
    0.44
    identified
    0.42
     monies
    0.42
    </code>
    0.41
    ocup
    0.41
    POSITIVE LOGITS
     लड़की
    0.56
     aneurysm
    0.52
     upoz
    0.52
     når
    0.50
    クロン
    0.50
    ভব
    0.48
    ംഗ്
    0.48
    ையை
    0.47
    槿
    0.47
     बताना
    0.47
    Activations Density 0.000%

    No Known Activations