© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    limited to specific use

    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_16_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
    )।
    1.29
     barcodes
    1.16
    ;
    1.16
    lardan
    1.13
     itineraries
    1.10
     tokamaks
    1.10
     olives
    1.09
     anions
    1.09
     rockers
    1.09
     oiseaux
    1.09
    POSITIVE LOGITS
    с
    1.14
    ิ
    1.13
     лишь
    1.12
    ่า
    1.11
    ш
    1.09
    ния
    1.04
    "
    0.99
    1
    0.98
    的技术
    0.98
    ן
    0.98
    Activations Density 0.125%

    No Known Activations