© 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. 16072
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     CITED
    -1.18
    ternut
    -1.09
    说实话
    -1.05
    網頁
    -1.03
    queness
    -1.02
     partic
    -1.02
    ela
    -1.01
     précip
    -1.00
    pone
    -1.00
    orija
    -0.99
    POSITIVE LOGITS
    这个
    1.00
    还有
    0.93
    </em>
    0.91
    mste
    0.90
     jogja
    0.89
     törvény
    0.88
     caneta
    0.88
     hina
    0.87
     که
    0.86
     herren
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.