© 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. 89795
    Prev
    Next
    INDEX
    Explanations

    words and pictures

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

    requires prescription or diagnosis

    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
    mRNA
    0.48
    OFF
    0.47
    燔
    0.47
    鍑
    0.46
    ن
    0.46
    ف
    0.46
    HERS
    0.46
    ↵
    0.45
    POSIX
    0.45
    ージャー
    0.45
    POSITIVE LOGITS
     rapidez
    0.55
     imprescind
    0.53
     allgemeinen
    0.51
     aisément
    0.50
     लिहाजा
    0.50
     allgeme
    0.50
     کھیلو
    0.50
    တည်
    0.50
     encuentren
    0.48
     tranquilidad
    0.48
    Activations Density 0.000%

    No Known Activations