© 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. 36188
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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
    ain
    1.34
    ді
    1.27
    ли
    1.26
    -
    1.20
    ми
    1.19
    ak
    1.17
    ா
    1.16
     excitatory
    1.15
    াস
    1.14
    ana
    1.13
    POSITIVE LOGITS
    ंत्रिकी
    1.26
    ০
    1.24
     의해
    1.20
    چین
    1.18
    ᱸ
    1.17
    ことで
    1.13
    ﺹ
    1.13
    IUM
    1.07
    𝔰
    1.05
    ும்
    1.02
    Activations Density 0.001%

    No Known Activations