© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 90273
    Prev
    Next
    INDEX
    Explanations

    invention, insulation, phone calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spire
    0.49
     basilica
    0.47
     lí
    0.46
     gia
    0.46
     cả
    0.46
    FAMILY
    0.46
     breeze
    0.45
    嫄
    0.45
    畱
    0.45
     Castle
    0.44
    POSITIVE LOGITS
     impressing
    0.57
    شوند
    0.54
    циона
    0.54
    (-
    0.49
     மிக்க
    0.48
     দক্ষ
    0.48
     иннова
    0.48
     evoking
    0.47
     قاب
    0.47
     مخ
    0.46
    Activations Density 0.000%

    No Known Activations