© 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. 91270
    Prev
    Next
    INDEX
    Explanations

    understanding or experience

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

    connector or highlights

    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
     系统
    0.53
     অস্ট্রেল
    0.51
     單
    0.49
    থাৎ
    0.47
    Soil
    0.47
     ऑस्ट्रेलिया
    0.47
     কম্পিউটার
    0.46
    સ્યા
    0.46
    ﹁
    0.46
     що
    0.45
    POSITIVE LOGITS
     COVID
    0.48
     IgG
    0.47
     infect
    0.46
     enn
    0.45
     epidemic
    0.44
     overt
    0.44
     menstru
    0.44
    sustaining
    0.43
     infectious
    0.43
     hygiene
    0.42
    Activations Density 0.001%

    No Known Activations