© 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. 70612
    Prev
    Next
    INDEX
    Explanations

    compiler, fruit, food

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

    clothing details and conditions

    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
     wanna
    0.52
    ]+
    0.48
    って
    0.48
    お待ち
    0.47
    %
    0.47
    懟
    0.46
    demand
    0.45
     as
    0.45
     atual
    0.44
     overcrowding
    0.44
    POSITIVE LOGITS
    肤
    0.46
    沢
    0.45
     তাহারই
    0.44
    编译器
    0.43
    номер
    0.42
    水果
    0.42
    руя
    0.42
    笕
    0.41
    食物
    0.41
     фрук
    0.41
    Activations Density 0.001%

    No Known Activations