© 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. 5652
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by Greek or other languages

    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
    s
    1.70
    sion
    1.05
    ের
    1.04
    sik
    1.00
    sus
    0.97
    sning
    0.96
    ों
    0.96
    𝘀
    0.94
    society
    0.91
    som
    0.89
    POSITIVE LOGITS
    り
    1.04
    ка
    0.92
    л
    0.90
    ்ய
    0.89
    ج
    0.89
    ി
    0.89
    ه
    0.87
    ام
    0.85
    هي
    0.84
    不容易
    0.84
    Activations Density 1.191%

    No Known Activations