© 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. 28351
    Prev
    Next
    INDEX
    Explanations

    numbers and URLs

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

    multilingual change and variation

    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
    (...
    0.46
     ближай
    0.45
    .\"
    0.45
    ++
    0.45
     TDs
    0.44
    ^{-}\
    0.44
    besar
    0.43
     (+)
    0.43
    BD
    0.43
    大きい
    0.43
    POSITIVE LOGITS
    امة
    0.48
    ن
    0.46
    جموعة
    0.45
    قم
    0.44
    ہنی
    0.44
    的故事
    0.43
    کروچ
    0.43
     گروپ
    0.42
    ரும
    0.42
    𝐚
    0.42
    Activations Density 0.000%

    No Known Activations