© 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. 82780
    Prev
    Next
    INDEX
    Explanations

    lawfully use standard compliant mezzanine

    np_acts-logits-general · gemini-2.5-flash-lite

    apologies and sincerity

    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
     ও
    0.49
    ীর
    0.46
     oraz
    0.46
     Identification
    0.46
     kult
    0.46
     bersifat
    0.46
     Shri
    0.45
    ã
    0.45
     Acquisition
    0.45
     Archa
    0.45
    POSITIVE LOGITS
    中间
    0.48
     ریاضی
    0.47
    Petit
    0.44
    Deposito
    0.43
    訾
    0.43
     שני
    0.43
    ዋል
    0.43
    MovieModal
    0.43
    MyShop
    0.43
    સ્થ
    0.43
    Activations Density 0.000%

    No Known Activations