© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80742
    Prev
    Next
    INDEX
    Explanations

    Acceleration, provide, ingredient, subgraph, local, fundamental, Birthday

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    رحمن
    0.47
     bonita
    0.47
     pend
    0.46
     compassion
    0.46
     books
    0.45
     humild
    0.44
     business
    0.44
     cms
    0.43
     bills
    0.42
    &#
    0.42
    POSITIVE LOGITS
    वी
    0.51
    Nickel
    0.50
    க்கல்
    0.50
     Recycling
    0.50
    鎳
    0.50
     നിര്‍
    0.50
    Calculating
    0.49
    獬
    0.49
    𝟬
    0.49
     строительства
    0.48
    Activations Density 0.003%

    No Known Activations