© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 24893
    Prev
    Next
    INDEX
    Explanations

    downloading content

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

    downloading reports, apps, files

    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
     camped
    0.54
    増や
    0.51
    اش
    0.51
    اشة
    0.50
    ܸ
    0.49
    Компания
    0.48
    }`}
    0.47
    ikt
    0.47
    펨
    0.47
     길이가
    0.47
    POSITIVE LOGITS
     herunter
    1.00
    下来
    0.90
    下来的
    0.90
     다운
    0.89
     download
    0.87
    下载
    0.87
    下來
    0.87
     downloading
    0.87
    DOWNLOAD
    0.86
    Download
    0.84
    Activations Density 0.057%

    No Known Activations