© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 92
    Prev
    Next
    INDEX
    Explanations

    unique or different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    न
    1.57
    स
    1.41
    ди
    1.38
    י
    1.28
    на
    1.27
    ন
    1.22
    т
    1.20
    ی
    1.18
     каме
    1.15
    вний
    1.06
    POSITIVE LOGITS
    。
    1.18
    。(
    1.10
    に
    1.09
    อยู่ที่
    1.08
    ।
    1.06
     博文
    1.05
    。「
    1.02
    ía
    0.98
    的主
    0.97
    臾
    0.97
    Activations Density 0.504%

    No Known Activations