© 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. 58575
    Prev
    Next
    INDEX
    Explanations

    significant financial

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

    development of sections

    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
    َات
    0.51
    镭
    0.50
     COUNTRY
    0.48
    typeparam
    0.47
     responde
    0.46
     vaguely
    0.46
    했는데
    0.45
    鐳
    0.45
     parmes
    0.45
    notlocked
    0.45
    POSITIVE LOGITS
     уро
    0.49
     bisogno
    0.49
    スイ
    0.47
     їх
    0.46
    を目
    0.44
     και
    0.44
     arbeid
    0.43
     высоту
    0.43
    ཐ
    0.43
     ו
    0.42
    Activations Density 0.001%

    No Known Activations