© 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. 103022
    Prev
    Next
    INDEX
    Explanations

    let lenders, your spirit, occurring conditions

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

    data sequence `cpp` songs

    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
    า
    0.51
    اسي
    0.49
    ا۔
    0.48
    anı
    0.46
    enciais
    0.46
     காலத்தில்
    0.44
    زين
    0.44
     견
    0.44
    дут
    0.43
     قار
    0.43
    POSITIVE LOGITS
     jumpers
    0.50
     machines
    0.49
     memberships
    0.48
     bowlers
    0.47
     advertisers
    0.47
     ladders
    0.47
     gj
    0.46
     enthusiasts
    0.46
     eaters
    0.46
     earners
    0.45
    Activations Density 0.001%

    No Known Activations