© 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. 46064
    Prev
    Next
    INDEX
    Explanations

    dark environments, Dutch flag

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

    also

    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
    數
    0.52
    狨
    0.47
    ادى
    0.47
    खिल
    0.47
    ਅ
    0.46
    釹
    0.46
     mág
    0.44
    器件
    0.43
    ব্যবহার
    0.43
    केमॉन
    0.43
    POSITIVE LOGITS
     illetve
    0.46
     freaking
    0.45
     dentro
    0.43
     deix
    0.43
     داخل
    0.42
     ترلاسه
    0.41
    畠
    0.41
     abril
    0.41
     apologizing
    0.40
     گ
    0.40
    Activations Density 0.000%

    No Known Activations