© 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. 97072
    Prev
    Next
    INDEX
    Explanations

    willing to

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

    KMS host key

    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
    💒
    0.47
    ⛪
    0.47
    Cosine
    0.46
    ന
    0.45
    uiar
    0.45
    ⌵
    0.43
    墳
    0.43
    GJ
    0.43
     masih
    0.42
     vogliamo
    0.42
    POSITIVE LOGITS
    وية
    0.52
    ഡിയോ
    0.48
     Inglaterra
    0.47
    പ്പം
    0.46
    ordering
    0.44
     order
    0.43
     compelling
    0.43
    珐
    0.43
    ټ
    0.43
    рио
    0.42
    Activations Density 0.001%

    No Known Activations