© 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-16K
    7. 14797
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-english characters

    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_16k_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
     electrónico
    1.28
     (\$
    1.22
    った
    1.21
    تيجة
    1.19
     I
    1.18
     absurd
    1.18
    ®,
    1.17
     stands
    1.16
    zelfde
    1.16
     erklärte
    1.15
    POSITIVE LOGITS
    Ди
    1.41
    ۵
    1.34
    أ
    1.29
    ‌تر
    1.28
    फ
    1.27
    О
    1.27
    ंत्रिकी
    1.18
    Κα
    1.17
    軍
    1.16
    Ко
    1.16
    Activations Density 0.003%

    No Known Activations