© 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. 16-GEMMASCOPE-2-RES-262K
    7. 50002
    Prev
    Next
    INDEX
    Explanations

    rocket thrust

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     shifting
    0.58
    tFileInputExcel
    0.53
    giveness
    0.53
    ᱗
    0.53
     lessening
    0.52
    nelle
    0.52
     शेवट
    0.51
     worsening
    0.50
     راستہ
    0.50
     reconciling
    0.49
    POSITIVE LOGITS
    א
    0.61
    في
    0.55
    ױ
    0.55
    호
    0.54
    وی
    0.54
    ów
    0.53
    ב
    0.53
    Α
    0.53
    ز
    0.52
    Ş
    0.51
    Activations Density 0.000%

    No Known Activations