© 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. 104515
    Prev
    Next
    INDEX
    Explanations

    supply

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

    White periods and gains

    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
     kullanımı
    0.55
     พูด
    0.55
    یب
    0.51
     menambah
    0.50
     ንጥረ
    0.49
     påver
    0.48
     وید
    0.48
     タ
    0.47
     式
    0.47
     も
    0.47
    POSITIVE LOGITS
    N
    0.54
    T
    0.53
    Y
    0.52
    reaching
    0.50
    "
    0.48
    W
    0.47
    O
    0.47
    tur
    0.46
    sky
    0.45
    rying
    0.45
    Activations Density 0.001%

    No Known Activations