© 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. 88608
    Prev
    Next
    INDEX
    Explanations

    recursion

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

    recursive or approximation

    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
    ุปกรณ์
    0.54
    DEVICE
    0.45
    舊
    0.45
    εται
    0.44
     Vikas
    0.44
    TLE
    0.43
    ται
    0.42
    醇
    0.41
    ઈ
    0.41
    حديد
    0.40
    POSITIVE LOGITS
    recursive
    0.51
     permissive
    0.47
     اکنون
    0.46
     symplectic
    0.44
     recurs
    0.43
     கொலை
    0.43
    жкой
    0.43
     recursive
    0.43
     recursion
    0.42
    atoires
    0.42
    Activations Density 0.001%

    No Known Activations