© 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. 229662
    Prev
    Next
    INDEX
    Explanations

    new members, weekly flash, authority work, to return, techniques at

    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
    କ
    0.59
    ପ
    0.55
     проект
    0.54
     organisatie
    0.51
    冠軍
    0.51
     језик
    0.50
    つき
    0.49
    нами
    0.48
    Ré
    0.48
     креп
    0.48
    POSITIVE LOGITS
     పూర్తి
    0.49
    ઁ
    0.47
    vonne
    0.46
     있
    0.43
     עם
    0.43
    ں
    0.43
     가까
    0.43
    überkü
    0.42
     therapy
    0.41
     hast
    0.41
    Activations Density 0.000%

    No Known Activations