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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222012
    Prev
    Next
    INDEX
    Explanations

    visa applications, medical Hg, technical ports

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

    Discover Places, debris fields

    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
    概念
    0.47
    fall
    0.47
     generalizing
    0.47
    |-\
    0.46
     கட்டடக்கலை
    0.45
     fall
    0.44
    ková
    0.44
    ವಾರು
    0.44
     அற்புதமான
    0.43
    olem
    0.43
    POSITIVE LOGITS
    จะต้อง
    0.49
     fortiter
    0.45
     decade
    0.43
    ेशा
    0.42
     disbursements
    0.42
    を通じて
    0.42
    श
    0.42
    чения
    0.42
     settim
    0.42
     Rhodesia
    0.41
    Activations Density 0.000%

    No Known Activations