© 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. 79913
    Prev
    Next
    INDEX
    Explanations

    design, model, name, job, data

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

    greetings and proper nouns

    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
     bachelor
    0.49
     belong
    0.44
     mares
    0.43
     have
    0.42
     provoke
    0.41
     mon
    0.41
     mut
    0.40
    ë
    0.40
     workmen
    0.40
     mamm
    0.39
    POSITIVE LOGITS
    大数据
    0.49
    ຕ້ອງ
    0.46
    나가
    0.45
     اداروں
    0.45
    /)
    0.45
    ផ្ត
    0.44
     데이터
    0.44
    xv
    0.44
    数据
    0.43
     डेटा
    0.43
    Activations Density 0.001%

    No Known Activations