© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123659
    Prev
    Next
    INDEX
    Explanations

    journal articles, medical data

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

    simple plans and physical qubits

    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
    Negative Logits
    ूतक
    0.50
     propriety
    0.48
    ي
    0.48
    疖
    0.46
    痱
    0.46
    squre
    0.45
    ೂರ್ಯ
    0.44
    نیا
    0.44
    िरण
    0.44
    ቋ
    0.44
    POSITIVE LOGITS
    OF
    0.50
    untuk
    0.45
     compartir
    0.45
    創作
    0.45
     chỗ
    0.44
     Dao
    0.43
    Untuk
    0.42
    COS
    0.41
     හා
    0.41
     PDC
    0.41
    Activations Density 0.002%

    No Known Activations