© 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. 80121
    Prev
    Next
    INDEX
    Explanations

    facility maintenance

    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
     イベント
    0.50
     IX
    0.48
    VIII
    0.48
     enables
    0.48
     VIII
    0.47
     பயன்படுகிறது
    0.47
     omoguć
    0.47
     leído
    0.46
     интересу
    0.46
    ゜
    0.46
    POSITIVE LOGITS
    arris
    0.45
    api
    0.43
     الز
    0.43
     पुन्हा
    0.43
    lind
    0.43
     Fr
    0.41
     Spill
    0.41
     Lindsey
    0.41
     تش
    0.41
    cez
    0.40
    Activations Density 0.000%

    No Known Activations