© 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. 301
    Prev
    Next
    INDEX
    Explanations

    temporal references

    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
    리
    0.86
    ó
    0.78
    ר
    0.76
    Descripción
    0.71
     Terbaik
    0.69
    ítható
    0.67
    uğ
    0.66
     Valores
    0.64
     Zeichen
    0.62
    פר
    0.62
    POSITIVE LOGITS
    mittag
    0.82
    يل
    0.77
    ilion
    0.75
    speople
    0.75
    pring
    0.74
     मनाने
    0.74
    એ
    0.73
     showers
    0.73
    の日
    0.71
    getP
    0.71
    Activations Density 1.260%

    No Known Activations