© 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. 97517
    Prev
    Next
    INDEX
    Explanations

    blots, swimming, willing

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

    shelter, context, images, seller 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
     완료
    0.51
    Execute
    0.48
    !!!!
    0.46
     执行
    0.46
    plating
    0.45
     ग्रस्त
    0.45
     \%
    0.45
    Execution
    0.45
     orifices
    0.45
     作業
    0.44
    POSITIVE LOGITS
    চন্দ্রের
    0.48
     Hid
    0.47
     Informal
    0.47
     Fid
    0.47
     UserRepository
    0.47
     Subram
    0.45
     Selective
    0.45
    츈
    0.45
     Meridian
    0.44
     Locomotive
    0.43
    Activations Density 0.000%

    No Known Activations