© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14544
    Prev
    Next
    INDEX
    Explanations

    what questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.06
     ebenfalls
    -1.01
     who
    -1.00
     Também
    -0.96
     també
    -0.91
    okohama
    -0.91
    probably
    -0.90
    ఁ
    -0.90
    сында
    -0.89
     how
    -0.88
    POSITIVE LOGITS
    𝟏
    1.01
    uyasha
    0.96
    ‌اند
    0.96
    ادگی
    0.95
     new
    0.94
    两者
    0.94
    ilets
    0.91
     melakukannya
    0.91
    Being
    0.91
    “……”
    0.91
    Activations Density 0.004%

    No Known Activations