© 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. 111094
    Prev
    Next
    INDEX
    Explanations

    for, between, times, free

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

    graphic descriptions

    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
    stattung
    0.52
    kennung
    0.48
    褛
    0.47
    涝
    0.46
    мести
    0.45
    Nicht
    0.44
     Outlet
    0.44
     liệu
    0.43
    काळ
    0.43
    笪
    0.43
    POSITIVE LOGITS
     convolution
    0.52
     convolutions
    0.49
     tremor
    0.48
     isom
    0.48
    cnn
    0.46
     horrifying
    0.46
     embrace
    0.44
     cls
    0.44
     coherence
    0.44
     Remington
    0.43
    Activations Density 0.001%

    No Known Activations