© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50753
    Prev
    Next
    INDEX
    Explanations

    department affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brazen
    0.45
     boulder
    0.42
     gegen
    0.41
    周囲
    0.39
     tous
    0.39
     tutti
    0.38
    ¿
    0.38
    ז
    0.38
     caída
    0.37
    рі
    0.37
    POSITIVE LOGITS
     Department
    1.00
    Department
    0.99
     Departamento
    0.79
     DEPARTMENT
    0.79
    DEPARTMENT
    0.77
     Departments
    0.77
     डिपार्टमेंट
    0.74
     departamento
    0.70
    department
    0.69
     Département
    0.69
    Activations Density 0.009%

    No Known Activations