© 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. 129071
    Prev
    Next
    INDEX
    Explanations

    documentation comments

    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
     그것
    -1.09
    jboss
    -0.97
    xfa
    -0.96
     damaligen
    -0.95
     Began
    -0.94
    않
    -0.93
    FIVE
    -0.92
     Тогда
    -0.91
     حدث
    -0.91
     воору
    -0.90
    POSITIVE LOGITS
     if
    1.34
     to
    1.24
     memiliki
    1.17
    ând
    1.09
    ška
    1.08
    Schule
    1.07
     mengal
    1.07
    恚
    1.04
     you
    1.03
    Ɩ
    1.03
    Activations Density 0.011%

    No Known Activations