© 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. 64656
    Prev
    Next
    INDEX
    Explanations

    organization and government entities

    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
     himself
    -0.94
    ILIO
    -0.82
     ministre
    -0.82
    太多了
    -0.82
     Himself
    -0.82
     testen
    -0.79
     обло
    -0.79
    alib
    -0.78
    cripcion
    -0.78
    cripción
    -0.78
    POSITIVE LOGITS
     verzorg
    0.93
     vermek
    0.85
     sending
    0.84
     længere
    0.82
    europa
    0.81
     bezoek
    0.79
    vám
    0.78
     święta
    0.78
     central
    0.77
     sær
    0.77
    Activations Density 0.070%

    No Known Activations