© 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-TRANSCODER-262K
    7. 48184
    Prev
    Next
    INDEX
    Explanations

    break up with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Arts
    0.39
     गठ
    0.38
     composée
    0.36
     überzeugt
    0.36
     participó
    0.35
     sécher
    0.35
    劦
    0.35
     वी
    0.34
    zut
    0.34
     насто
    0.34
    POSITIVE LOGITS
    Break
    0.66
     Break
    0.58
     break
    0.55
    BREAK
    0.54
     breakage
    0.52
    break
    0.50
     broke
    0.49
    breakable
    0.48
     BREAK
    0.47
     breaking
    0.47
    Activations Density 0.001%

    No Known Activations