© 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. 209060
    Prev
    Next
    INDEX
    Explanations

    retail stores, religion, personal experience

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

    for a

    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
    Nombre
    0.49
    DOCT
    0.48
    RH
    0.47
    Ciudad
    0.47
    Orig
    0.46
    H
    0.46
    MJ
    0.45
    Zu
    0.45
    Mâ
    0.45
    SAMPLE
    0.45
    POSITIVE LOGITS
     पटाखों
    0.49
     capas
    0.48
     पिछड़े
    0.48
    炲
    0.46
     চেয়েছিলেন
    0.46
    ят
    0.46
     স্টি
    0.45
     跳转
    0.45
     ดังนั้น
    0.43
     সহজাত
    0.43
    Activations Density 0.000%

    No Known Activations