© 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. 36628
    Prev
    Next
    INDEX
    Explanations

    puts up

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

    dampness and cold

    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
    у
    0.58
    comprom
    0.45
    說明
    0.45
    وض
    0.45
     compromise
    0.44
    僥
    0.44
    ع
    0.43
    람
    0.43
    Ꮮ
    0.42
    ورس
    0.42
    POSITIVE LOGITS
     бю
    0.55
     граф
    0.55
     বৌ
    0.52
     ঈশ্বর
    0.51
     февра
    0.50
     кампа
    0.48
     нашем
    0.47
    erçe
    0.47
     চৌ
    0.47
     hampir
    0.46
    Activations Density 0.000%

    No Known Activations