© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25294
    Prev
    Next
    INDEX
    Explanations

    student life and experiences

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

    student

    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_31_width_262k_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
    та
    0.86
    தி
    0.83
    อีก
    0.79
    لی
    0.75
    चा
    0.75
    يون
    0.74
    غ
    0.72
    on
    0.71
    به
    0.71
    ό
    0.70
    POSITIVE LOGITS
     Students
    1.18
     Student
    1.16
     الطلاب
    1.15
     학생
    1.12
    Students
    1.10
     STUDENTS
    1.05
    Student
    1.04
     وطالبات
    0.99
     students
    0.98
     студент
    0.98
    Activations Density 0.054%

    No Known Activations