© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130355
    Prev
    Next
    INDEX
    Explanations

    providers agree, beautiful new, shipping ways

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

    Meaning, check, morph, implementation, new, P, direct

    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
    Negative Logits
    恫
    0.49
    旨在
    0.47
    编写
    0.47
     அவற்ற
    0.46
     Ваши
    0.45
     இதுபோன்ற
    0.45
     DataFrame
    0.45
     दुनियाभर
    0.45
     Groundwater
    0.45
    itung
    0.45
    POSITIVE LOGITS
     нього
    0.52
     njega
    0.50
     に
    0.47
     hippocampus
    0.46
     hundred
    0.46
     också
    0.46
     سے
    0.44
    сюда
    0.44
     puente
    0.43
     ওখানে
    0.43
    Activations Density 0.001%

    No Known Activations