© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5233
    Prev
    Next
    INDEX
    Explanations

    citizen, citrine, senior, citizens

    np_acts-logits-general · gemini-2.5-flash-lite

    citizen, citizenship, citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सुपारी
    0.40
     swo
    0.39
     installer
    0.39
     sparsebundle
    0.39
    絟
    0.39
    కం
    0.38
     Encoder
    0.37
    颔
    0.37
    Encoder
    0.36
     بکر
    0.36
    POSITIVE LOGITS
     citizen
    3.94
     Citizen
    3.91
     Citizens
    3.89
    citizens
    3.83
    Citizen
    3.83
    Citizens
    3.81
     citizens
    3.75
     cit
    3.70
     citiz
    3.70
     Cit
    3.58
    Activations Density 0.210%

    No Known Activations