© 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. 24699
    Prev
    Next
    INDEX
    Explanations

    describing items and requirements

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

    mathematics formulas

    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
    ’
    0.52
     Первая
    0.44
    хом
    0.43
     mãos
    0.42
    s
    0.41
     যদি
    0.39
    耐心
    0.39
     Такая
    0.39
    那個
    0.39
     venido
    0.39
    POSITIVE LOGITS
    回顾
    0.52
     \{
    0.45
     ट्रैक
    0.45
    Ⴌ
    0.44
     eliminate
    0.43
     selectively
    0.43
     eliminación
    0.42
     ihtiy
    0.42
     elimin
    0.41
     facilitate
    0.41
    Activations Density 0.000%

    No Known Activations