© 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. 204363
    Prev
    Next
    INDEX
    Explanations

    Listing provided

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

    define questions

    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
     एनर्जी
    0.42
    しやすい
    0.40
    uların
    0.40
    押し
    0.40
    一つの
    0.39
    磨
    0.39
    打ち
    0.38
     elongated
    0.38
     purposely
    0.38
     unjustified
    0.38
    POSITIVE LOGITS
    ادم
    0.59
    engelsk
    0.49
     现在
    0.49
    恿
    0.47
     Vogue
    0.47
     ，
    0.46
    upta
    0.46
     først
    0.46
     Fashion
    0.46
    Avro
    0.46
    Activations Density 0.000%

    No Known Activations