© 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. 178071
    Prev
    Next
    INDEX
    Explanations

    medical alert bracelets

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

    childhood context

    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
     goodies
    0.57
    𝔬
    0.55
     получаем
    0.54
     almighty
    0.52
    優惠
    0.50
    ہ
    0.50
     ہوئی
    0.49
    𝖒
    0.49
    待ち
    0.48
     Якщо
    0.48
    POSITIVE LOGITS
     contexts
    0.52
     exacerbated
    0.48
     parenchyma
    0.47
     traced
    0.45
     implicated
    0.45
    influenced
    0.45
     corrobor
    0.45
     contextos
    0.45
     संदर्भ
    0.45
     hypothesized
    0.45
    Activations Density 0.001%

    No Known Activations