© 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. 48716
    Prev
    Next
    INDEX
    Explanations

    business, property, or product descriptions

    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
    扫
    0.51
    Ử
    0.47
    运维
    0.47
    IZED
    0.46
    LEV
    0.46
    可持续
    0.46
    巨
    0.45
    USU
    0.45
    尔
    0.45
    НЫ
    0.44
    POSITIVE LOGITS
     commuter
    0.50
     seaside
    0.48
     humiliation
    0.48
     court
    0.47
     loophole
    0.46
    iencia
    0.45
     collie
    0.45
     immigration
    0.45
     foray
    0.45
     cellar
    0.44
    Activations Density 0.001%

    No Known Activations