© 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. 34-GEMMASCOPE-RES-131K
    7. 78716
    Prev
    Next
    INDEX
    Explanations

    magistrate followed by name or court

    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_34/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
    SessionFactory
    -0.68
     judges
    -0.65
    ורים
    -0.65
     пад
    -0.64
     judge
    -0.63
    Judges
    -0.63
    transient
    -0.63
    總統
    -0.63
    judge
    -0.63
    Sky
    -0.63
    POSITIVE LOGITS
     magistrate
    2.33
     Magistrate
    2.17
     magistrates
    2.13
     Magistrates
    1.81
    Mag
    1.60
    mag
    1.52
     magist
    1.45
     mag
    1.44
     Magist
    1.39
     magister
    1.31
    Activations Density 0.064%

    No Known Activations