© 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-16K
    7. 757
    Prev
    Next
    INDEX
    Explanations

    integers

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     multiplicities
    0.25
     externalities
    0.25
     neighbourhoods
    0.25
     hemodynamic
    0.24
     cadres
    0.24
     migrants
    0.24
     bronchi
    0.23
     crimes
    0.23
     thromb
    0.23
    ’:
    0.23
    POSITIVE LOGITS
    atti
    0.32
    और
    0.31
    so
    0.30
    And
    0.30
    पु
    0.30
    Unfortunately
    0.30
    This
    0.29
    email
    0.29
    谢谢
    0.29
    orma
    0.29
    Activations Density 0.842%

    No Known Activations