© 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. 200218
    Prev
    Next
    INDEX
    Explanations

    T5 variants and MBART

    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
     to
    0.58
     thick
    0.48
     Jamal
    0.47
     Understanding
    0.47
     Ensuring
    0.47
     AER
    0.46
     a
    0.46
     AB
    0.46
     Refining
    0.46
     Determining
    0.45
    POSITIVE LOGITS
    ﺓ
    0.51
    organizzazione
    0.50
    iciones
    0.49
     müşter
    0.49
    вые
    0.48
    preco
    0.48
    ные
    0.47
    łączy
    0.47
    zovaniyu
    0.46
    żą
    0.46
    Activations Density 0.006%

    No Known Activations