© 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. 221741
    Prev
    Next
    INDEX
    Explanations

    design or layout

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

    Minimum hardware, security risks

    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
    γραφ
    0.50
    グラフ
    0.49
    elsk
    0.46
    Im
    0.46
    睦
    0.45
    中医
    0.45
    रांत
    0.44
    ଢ
    0.43
    ्रीम
    0.43
    графи
    0.43
    POSITIVE LOGITS
     भविष्य
    0.52
     برق
    0.52
     ياس
    0.51
     invaluable
    0.49
     जीएस
    0.49
     യുവാ
    0.48
     حاول
    0.48
    .‏
    0.48
     ته
    0.47
     ให้
    0.47
    Activations Density 0.001%

    No Known Activations