© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11361
    Prev
    Next
    INDEX
    Explanations

    woke or awaken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ों
    1.12
    ्य
    1.00
    ׁ
    0.97
     noires
    0.93
    ก
    0.92
    ુ
    0.91
     congregate
    0.88
    ますが
    0.86
    تها
    0.86
    มิ
    0.84
    POSITIVE LOGITS
    ский
    0.87
    が多く
    0.86
    ﻟ
    0.84
    ist
    0.82
    ፨
    0.82
    𝒊
    0.81
    此之外
    0.81
    ﺹ
    0.80
    걀
    0.80
    ية
    0.78
    Activations Density 0.001%

    No Known Activations