© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127842
    Prev
    Next
    INDEX
    Explanations

    introduced, created, aimed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     آمریکایی
    -1.13
    ⅽ
    -1.05
    ֶּ
    -1.02
    middag
    -1.02
    Tikang
    -1.01
    []}
    -0.99
    Currently
    -0.99
    tifiable
    -0.98
    ssssssss
    -0.98
     cargador
    -0.98
    POSITIVE LOGITS
     aims
    1.52
     aim
    1.37
     nhằm
    1.32
    ὕ
    1.28
    ığımız
    1.27
     wanted
    1.27
    ємо
    1.27
     we
    1.26
     aimed
    1.23
    はこの
    1.23
    Activations Density 0.027%

    No Known Activations