© 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. 65784
    Prev
    Next
    INDEX
    Explanations

    shower designs

    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
     plát
    -1.31
     šaty
    -1.22
     camisetas
    -1.08
     チラ
    -1.05
     nowej
    -1.04
     calabaza
    -1.03
    Tahun
    -1.02
    킁
    -1.01
     inmedi
    -1.01
     gouvern
    -1.00
    POSITIVE LOGITS
    摂取
    1.08
    per
    1.01
    </em>
    0.98
     set
    0.92
    z
    0.91
     T
    0.91
    </strong>
    0.90
     worin
    0.89
     Kriege
    0.89
    rdoba
    0.89
    Activations Density 0.002%

    No Known Activations