© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 30325
    Prev
    Next
    INDEX
    Explanations

    Embassy or Consulate

    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
    ij
    1.98
    ۰
    1.70
    ycling
    1.59
    chainId
    1.55
     وعلى
    1.55
    mainWindow
    1.53
    शंस
    1.47
    getSource
    1.47
    annya
    1.46
     स्टेट
    1.45
    POSITIVE LOGITS
    Ве
    2.47
    ти
    2.30
    س
    2.27
    ﺗ
    2.23
    で
    2.22
    𝒐
    2.20
    ৯
    2.17
    П
    2.16
    С
    2.09
    𝒆
    2.09
    Activations Density 0.000%

    No Known Activations