© 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. 116648
    Prev
    Next
    INDEX
    Explanations

    law and legal services

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

    day filled with

    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
    ↵
    0.56
     UM
    0.48
    c
    0.47
    !=
    0.47
    !
    0.47
    0.46
    一一
    0.46
     ú
    0.46
     demean
    0.46
     !
    0.45
    POSITIVE LOGITS
    設施
    0.55
     भरने
    0.53
    导弹
    0.49
     भाषण
    0.48
    ंजनों
    0.48
    尭
    0.48
    邳
    0.47
    Therates
    0.47
    輥
    0.46
     रोजगार
    0.46
    Activations Density 0.000%

    No Known Activations