© 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. 229565
    Prev
    Next
    INDEX
    Explanations

    innovations, yield, pop off

    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
     conservatively
    0.46
    ż
    0.46
    の違い
    0.45
     Rivals
    0.45
     conservative
    0.45
    wild
    0.45
     Lamp
    0.44
     Israelis
    0.44
    の使用
    0.44
    conserv
    0.44
    POSITIVE LOGITS
     artikel
    0.48
     muzik
    0.48
     struktur
    0.47
     blok
    0.46
    adeloupe
    0.45
     ट
    0.45
     projek
    0.44
    阵容
    0.44
     projekt
    0.44
    љи
    0.44
    Activations Density 0.001%

    No Known Activations