© 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. 80369
    Prev
    Next
    INDEX
    Explanations

    `to worship`, `just for`, `of South`, `layered challenge`

    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
     curation
    0.46
     interpr
    0.46
    ک
    0.45
    вание
    0.45
     upregulation
    0.44
     урав
    0.44
     interpretation
    0.43
     Пу
    0.43
    힐
    0.43
     interpreta
    0.43
    POSITIVE LOGITS
    which
    0.46
    rukt
    0.45
    ished
    0.42
    tsk
    0.42
    igree
    0.41
    oha
    0.41
     }^{(
    0.40
    ti
    0.40
    start
    0.40
    olt
    0.40
    Activations Density 0.023%

    No Known Activations