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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41598
    Prev
    Next
    INDEX
    Explanations

    study in or study of

    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_31_width_262k_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
    al
    0.79
    ला
    0.78
    il
    0.67
    lington
    0.64
    2
    0.63
    ani
    0.62
    مان
    0.62
    ur
    0.62
    IC
    0.62
    estä
    0.61
    POSITIVE LOGITS
     изу
    0.99
     étudier
    0.95
     STUDY
    0.94
     الدراسة
    0.92
     enunciado
    0.86
     study
    0.86
     estudar
    0.83
    ス
    0.82
     изучения
    0.81
    Study
    0.80
    Activations Density 0.021%

    No Known Activations