© 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. 173234
    Prev
    Next
    INDEX
    Explanations

    gets described state

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

    gets to the heart of

    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
    信息
    0.54
    verständ
    0.51
    ImageIcon
    0.50
     ଜ
    0.50
    aneamente
    0.50
    getInfo
    0.49
    知らせ
    0.48
    حة
    0.48
     ინფორმა
    0.48
    フィー
    0.47
    POSITIVE LOGITS
    د
    0.48
    न्थ
    0.46
     Yayın
    0.45
    辶
    0.43
     prosecuted
    0.43
     trials
    0.43
     clim
    0.41
     brackets
    0.41
     llevado
    0.41
     gets
    0.41
    Activations Density 0.239%

    No Known Activations