© 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. 185554
    Prev
    Next
    INDEX
    Explanations

    unique products and services

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

    corporate jargon or buzzwords

    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
    UC
    0.54
     Patrim
    0.49
    RC
    0.47
    unak
    0.43
    hecy
    0.43
    RA
    0.42
    ISR
    0.42
    typ
    0.42
    Muscle
    0.41
    ↵
    0.41
    POSITIVE LOGITS
     besonder
    0.57
     particuliers
    0.50
     سابقا
    0.50
     idéale
    0.50
     äußerst
    0.49
     ঘনিষ্ঠভাবে
    0.48
     précédemment
    0.47
     adhé
    0.46
     apprend
    0.46
     attuned
    0.46
    Activations Density 0.000%

    No Known Activations