© 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. 109706
    Prev
    Next
    INDEX
    Explanations

    American or variation of words

    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
     poems
    0.57
     poema
    0.51
     exposes
    0.51
     pixie
    0.50
     woes
    0.49
     adds
    0.48
     चाहर
    0.47
     promoc
    0.47
     괜
    0.47
     presents
    0.47
    POSITIVE LOGITS
     امریکا
    0.48
    틱
    0.45
     Meteorology
    0.43
     امریک
    0.43
     ತಿಳಿದ
    0.42
    UnderTest
    0.42
     Bases
    0.41
    احث
    0.41
    貸
    0.41
    غیر
    0.40
    Activations Density 0.003%

    No Known Activations