© 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. 79114
    Prev
    Next
    INDEX
    Explanations

    listing items and their properties

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

    numbers, punctuation, and descriptions

    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
     alla
    0.43
    ？
    0.40
    )?
    0.39
     ench
    0.39
    」
    0.39
    ↵
    0.39
     one
    0.39
     ist
    0.39
    ？」
    0.38
     ผ่าน
    0.37
    POSITIVE LOGITS
     ஏக்க
    0.41
    িবদ্ধ
    0.39
    adinya
    0.38
    <unused1135>
    0.37
    lardı
    0.37
    萘
    0.37
    ক্টর
    0.37
     newApproved
    0.37
    <unused1043>
    0.37
    imbangkan
    0.37
    Activations Density 0.100%

    No Known Activations