© 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. 149819
    Prev
    Next
    INDEX
    Explanations

    web addresses

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

    URL closing parenthesis

    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
     Нужно
    0.46
    यूज
    0.45
    环境下
    0.44
     Där
    0.44
    Paras
    0.43
    来看看
    0.43
     unge
    0.43
    𝘧
    0.43
    Pel
    0.42
     Hick
    0.42
    POSITIVE LOGITS
     frontend
    0.48
     breast
    0.43
     setTheme
    0.43
     ہونا
    0.42
     commands
    0.41
     front
    0.40
     theory
    0.40
     fronts
    0.39
     nitrile
    0.39
     stands
    0.38
    Activations Density 0.013%

    No Known Activations