© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 50013
    Prev
    Next
    INDEX
    Explanations

    interrelated effects, relationships, integration

    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
    Negative Logits
    మ
    0.49
    چه
    0.48
    ン
    0.46
    φ
    0.46
    ور
    0.46
    ag
    0.46
    is
    0.45
     breaker
    0.44
    "
    0.44
    <h2>
    0.44
    POSITIVE LOGITS
     طریقے
    0.55
    ವರಿಗೆ
    0.53
    伦敦
    0.52
    泞
    0.50
     ڕ
    0.49
     व्यक्ती
    0.49
    𝑅
    0.48
     سرطان
    0.48
     युद्ध
    0.46
    neyland
    0.46
    Activations Density 0.000%

    No Known Activations