© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235642
    Prev
    Next
    INDEX
    Explanations

    tail carriage, five percent, grocery store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    eye
    0.44
     Regulation
    0.43
    করণ
    0.42
    aa
    0.41
    hadoop
    0.40
    ＋
    0.40
     लग
    0.39
    :',
    0.39
    ారు
    0.39
    ++',
    0.39
    POSITIVE LOGITS
    ബ്രുവരി
    0.41
    roben
    0.40
     hinzu
    0.39
    രെ
    0.39
     initio
    0.39
     continuamos
    0.39
     persiste
    0.38
     caballo
    0.38
     afterthought
    0.38
    െ
    0.38
    Activations Density 0.000%

    No Known Activations