© 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. 109433
    Prev
    Next
    INDEX
    Explanations

    fabric and manufacturing

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

    temporary benefits

    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
    ে
    0.42
    蓉
    0.42
     Ново
    0.40
     placed
    0.40
    机会
    0.40
     blinked
    0.39
    swing
    0.39
    </a>
    0.39
    west
    0.39
    ֵ
    0.38
    POSITIVE LOGITS
     बहुतेक
    0.46
     Abelian
    0.46
     fabricant
    0.46
     Zika
    0.45
     slučaj
    0.44
     publishers
    0.43
     رفتار
    0.43
     smugglers
    0.42
     sharpen
    0.42
     पोलिसांनी
    0.42
    Activations Density 0.002%

    No Known Activations