© 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. 84443
    Prev
    Next
    INDEX
    Explanations

    recent order, exhibition, climbing, Apple

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

    Rapid rise

    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
    는
    0.61
     рее
    0.54
    ان
    0.52
     indicative
    0.47
    は
    0.47
     inaccuracies
    0.46
     lineal
    0.46
     intermittent
    0.45
    人形
    0.45
     upward
    0.44
    POSITIVE LOGITS
     Shik
    0.55
     Thời
    0.55
    लिस
    0.53
     Ciência
    0.52
     ponú
    0.52
     Thủ
    0.51
     shik
    0.50
    ણમાં
    0.50
    奻
    0.50
     módulo
    0.50
    Activations Density 0.001%

    No Known Activations