© 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. 63888
    Prev
    Next
    INDEX
    Explanations

    information and logistics

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

    evaluativeorqualitative

    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
    देशीर
    0.49
     ಕೂ
    0.47
     ویڈیو
    0.47
    どのような
    0.47
     म्यूचुअल
    0.47
     знали
    0.46
     controladores
    0.45
    ⤒
    0.45
     ήταν
    0.45
     furono
    0.45
    POSITIVE LOGITS
    س
    0.54
     OK
    0.52
     Der
    0.51
     ok
    0.50
     tr
    0.49
    der
    0.48
     sm
    0.48
     ML
    0.48
     Tr
    0.48
     IMPORT
    0.48
    Activations Density 0.000%

    No Known Activations