© 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. 180759
    Prev
    Next
    INDEX
    Explanations

    topics keywords

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

    production technology development

    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
     Україні
    0.52
     accented
    0.51
    硬盘
    0.51
     ejected
    0.49
     ৬৬
    0.49
    充满了
    0.47
    掂
    0.47
     articoli
    0.46
     inspected
    0.46
     swelled
    0.46
    POSITIVE LOGITS
    il
    0.44
    Calling
    0.44
    Human
    0.43
     Human
    0.42
    MIER
    0.41
    ırmaya
    0.41
    How
    0.40
    chee
    0.40
    AN
    0.39
    о
    0.39
    Activations Density 0.000%

    No Known Activations