© 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. 94722
    Prev
    Next
    INDEX
    Explanations

    describing spaces, pets, rollers

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

    tracking, already, player, prevent

    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
    pcion
    0.49
    產
    0.48
    迅
    0.47
    强
    0.47
    就是
    0.46
    重要
    0.46
    猛
    0.46
    原型
    0.46
    重要的
    0.45
    出
    0.45
    POSITIVE LOGITS
     attrezz
    0.50
     Straße
    0.49
     frais
    0.48
     espaces
    0.47
     replying
    0.46
     اختی
    0.46
     également
    0.44
     ola
    0.43
     брат
    0.43
     offrant
    0.43
    Activations Density 0.000%

    No Known Activations