© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33892
    Prev
    Next
    INDEX
    Explanations

    parentheses or list end

    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
     and
    -1.09
     ако
    -1.00
    seded
    -0.99
     outlier
    -0.98
    hubanes
    -0.97
    lateinit
    -0.93
    шайте
    -0.93
    ستر
    -0.90
     siguió
    -0.89
    łem
    -0.89
    POSITIVE LOGITS
    暧
    1.13
     externo
    1.11
     словно
    1.07
    лас
    1.06
    此外
    1.06
    妩
    1.05
     mechanisms
    1.04
    karan
    1.02
     गर्न
    1.00
    Ẁ
    1.00
    Activations Density 0.073%

    No Known Activations