© 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. 63547
    Prev
    Next
    INDEX
    Explanations

    accommodation at, seller’s, how much, alterable

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

    evaluations, advice, or descriptions

    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
    嵐
    0.47
     않는
    0.45
     ३
    0.45
     Recife
    0.45
     teníamos
    0.44
     contrad
    0.43
     Temos
    0.43
    갚
    0.42
     inhibition
    0.42
    lage
    0.42
    POSITIVE LOGITS
    मॉडल
    0.44
    搭配
    0.42
     standaard
    0.42
    Continental
    0.41
    Dockerfile
    0.40
    试验
    0.40
    ینګ
    0.39
     Logistics
    0.39
    publish
    0.39
     Swords
    0.39
    Activations Density 0.000%

    No Known Activations