© 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. 247759
    Prev
    Next
    INDEX
    Explanations

    custom specifications

    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
     Бүгенге
    0.55
    whenever
    0.54
    Ж
    0.51
    фия
    0.50
     вслед
    0.49
    𝚇
    0.49
     уравнения
    0.48
     สืบค้นเมื่อ
    0.48
     приорите
    0.48
    Projection
    0.47
    POSITIVE LOGITS
     tome
    0.48
     creep
    0.46
     grossly
    0.46
     wrong
    0.44
    墙
    0.43
    y
    0.43
     collagen
    0.43
     rushed
    0.42
    合成
    0.42
    直径
    0.42
    Activations Density 0.001%

    No Known Activations