© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    if then constraint

    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
     roused
    0.46
     prodig
    0.44
     vatten
    0.43
    ൪
    0.42
     pathogenicity
    0.42
     pathological
    0.41
     organização
    0.41
     rout
    0.40
     archiv
    0.40
     chauss
    0.40
    POSITIVE LOGITS
    p
    0.51
    the
    0.50
    variable
    0.48
    pere
    0.46
    shares
    0.45
    rivi
    0.45
    this
    0.45
     Matching
    0.44
    APER
    0.44
     प्लस
    0.43
    Activations Density 0.006%

    No Known Activations