© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 833
    Prev
    Next
    INDEX
    Explanations

    Japanese, Korean, Hindi, Basque, Persian greetings

    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_31_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
    CurrentByte
    0.87
    ちゃんの
    0.84
    ងឺ
    0.82
    единенных
    0.79
    Callories
    0.77
    കളുടെ
    0.76
    饉
    0.75
     পেয়েছিলাম
    0.75
    ക്കളുടെ
    0.74
    扨
    0.74
    POSITIVE LOGITS
     했
    0.92
     자
    0.81
     가능
    0.80
    하고
    0.80
     olur
    0.79
     다
    0.77
    uyor
    0.77
    abil
    0.76
     보
    0.76
     하고
    0.75
    Activations Density 0.022%

    No Known Activations