© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144116
    Prev
    Next
    INDEX
    Explanations

    available to buy or download

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

    evolution, excited, tactics, communication, capacity

    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
     ViewGroup
    0.54
     masonry
    0.50
    ্যাং
    0.50
    㑬
    0.48
    <0x0E>
    0.46
    㠱
    0.46
    䂙
    0.46
    墘
    0.46
     Dedicated
    0.45
     bangunan
    0.45
    POSITIVE LOGITS
    readers
    0.53
    gradients
    0.52
     veterinarians
    0.52
    intestinal
    0.51
     एनिमल
    0.50
    genetic
    0.49
    gradient
    0.48
    urgent
    0.47
     persecuted
    0.46
    scientists
    0.46
    Activations Density 0.002%

    No Known Activations