© 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. 27703
    Prev
    Next
    INDEX
    Explanations

    private sectors or 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
    strap
    -1.03
    ignment
    -0.98
    urized
    -0.97
    irée
    -0.97
    lwjgl
    -0.97
    necked
    -0.96
    bearded
    -0.94
    nese
    -0.93
     pihaknya
    -0.93
    ledad
    -0.92
    POSITIVE LOGITS
     private
    1.77
     privada
    1.62
     privately
    1.52
    私
    1.44
     PRIVATE
    1.41
     Private
    1.39
    private
    1.31
    Private
    1.27
    PRIVATE
    1.27
     privata
    1.25
    Activations Density 0.049%

    No Known Activations