© 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. 41-GEMMASCOPE-2-RES-262K
    7. 9548
    Prev
    Next
    INDEX
    Explanations

    common sense

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ឹង
    0.53
    任意
    0.52
    ្នាំ
    0.52
    ាត
    0.52
     وبركاته
    0.51
    ើម
    0.51
     innumerable
    0.50
    ENSIVE
    0.50
    ឺ
    0.50
    RENGTH
    0.49
    POSITIVE LOGITS
    alities
    0.91
    ality
    0.78
     misconceptions
    0.68
    ari
    0.67
     misconception
    0.66
    er
    0.64
    Sense
    0.63
     Mistakes
    0.63
    ale
    0.62
     Sense
    0.61
    Activations Density 0.004%

    No Known Activations