© 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. 40-GEMMASCOPE-2-RES-262K
    7. 8526
    Prev
    Next
    INDEX
    Explanations

    training and completing courses

    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_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
     deletion
    0.41
     dimensionless
    0.40
     poet
    0.40
     minuten
    0.39
    斤
    0.39
    祀
    0.38
    詩
    0.38
     deterministic
    0.38
    摘
    0.38
     delete
    0.38
    POSITIVE LOGITS
     training
    2.16
    培训
    2.03
    Training
    2.00
     Training
    1.99
    training
    1.96
     trainings
    1.95
     courses
    1.92
     pelatihan
    1.92
     प्रशिक्षण
    1.90
     обучения
    1.82
    Activations Density 0.063%

    No Known Activations