© 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. 218041
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    describing specific contexts

    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
    ت
    0.48
    electron
    0.46
    Insider
    0.42
    हूं
    0.42
    bley
    0.41
    зем
    0.41
    Buyers
    0.41
    ↵
    0.41
     famous
    0.41
    Tay
    0.40
    POSITIVE LOGITS
    깎
    0.53
     Aprili
    0.53
    Ꮑ
    0.50
     Parlament
    0.50
     Qualifier
    0.50
     Hukum
    0.49
     அதனை
    0.49
     сосед
    0.49
     Nama
    0.48
     налого
    0.48
    Activations Density 0.000%

    No Known Activations