© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    programs and instructors

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

    classes, courses, workshops

    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
     मिर
    0.41
    solve
    0.40
    prayer
    0.40
    ड़ब
    0.40
    erset
    0.40
    embrance
    0.39
    tolerance
    0.39
    舆
    0.39
    =((
    0.38
    orthogonal
    0.38
    POSITIVE LOGITS
     Instructor
    1.96
     instructor
    1.95
     instructors
    1.91
    Instructor
    1.85
    instructor
    1.80
     classes
    1.71
     수업
    1.59
     clases
    1.58
    classes
    1.56
     Classes
    1.56
    Activations Density 0.514%

    No Known Activations