© 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. 167704
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    rooted in negative 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
    myapp
    0.42
     дизайна
    0.40
    முக
    0.39
    சனம்
    0.39
    es
    0.39
     மொத்தம்
    0.38
    enna
    0.37
    os
    0.37
    சாக
    0.37
    "</
    0.37
    POSITIVE LOGITS
     archivo
    0.50
     aisa
    0.49
    ᒋ
    0.48
     masonry
    0.46
     mutex
    0.46
    ጀመሪያ
    0.45
     theorem
    0.45
     zákon
    0.44
     cistern
    0.43
     exercice
    0.43
    Activations Density 0.000%

    No Known Activations