© 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. 172675
    Prev
    Next
    INDEX
    Explanations

    law

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

    isolates data

    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
    ค้า
    0.52
    🎁
    0.44
    ellik
    0.43
    anek
    0.42
     avoir
    0.41
    ต่อ
    0.40
     우리는
    0.40
    地的
    0.40
     बायो
    0.40
     filesize
    0.39
    POSITIVE LOGITS
    رے
    0.44
    multiSelectList
    0.44
    MANAGER
    0.43
     symbolic
    0.42
    酩
    0.42
    MoodAnalyser
    0.41
    瘸
    0.41
    katore
    0.41
     જાય
    0.41
     persegu
    0.40
    Activations Density 0.000%

    No Known Activations