© 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. 71916
    Prev
    Next
    INDEX
    Explanations

    speaking or stating facts

    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
    说过
    -1.00
    ENIX
    -1.00
    othelial
    -0.96
     ALWAYS
    -0.96
    ámos
    -0.94
     delivers
    -0.93
    さんです
    -0.93
     a
    -0.93
     शुर
    -0.92
    リニューアル
    -0.92
    POSITIVE LOGITS
     your
    1.22
     yourself
    1.09
     chcesz
    1.05
     вашего
    1.02
     favoritos
    1.02
     point
    0.95
     otras
    0.94
    漂亮的
    0.94
     foe
    0.94
     innych
    0.94
    Activations Density 0.017%

    No Known Activations