© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65385
    Prev
    Next
    INDEX
    Explanations

    attorney and prosecutor titles

    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
     brokerage
    -0.87
     mobilier
    -0.79
    Governance
    -0.78
    馒头
    -0.77
    🦪
    -0.76
    Broker
    -0.75
     Menus
    -0.75
     péché
    -0.75
     multicolore
    -0.75
    TRX
    -0.74
    POSITIVE LOGITS
     prosecutor
    2.91
     prosecutors
    2.81
    Prosecutors
    2.39
    Prosec
    2.36
     Prosec
    2.31
     Prosecutor
    2.30
     prosecuting
    2.28
     prosec
    2.19
     prosecution
    1.79
     prosecuted
    1.72
    Activations Density 0.165%

    No Known Activations