© 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. 6676
    Prev
    Next
    INDEX
    Explanations

    freshness and representation

    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
    не
    1.01
    т
    0.95
    吗
    0.91
    ué
    0.88
     Are
    0.86
    。
    0.86
    녕
    0.86
    ен
    0.86
     Gently
    0.86
     In
    0.83
    POSITIVE LOGITS
    nuevo
    1.04
    Estos
    1.02
    vät
    0.95
    mény
    0.93
    വ്ര
    0.92
    köz
    0.91
    datos
    0.89
    wanza
    0.88
    入院
    0.86
    йки
    0.86
    Activations Density 0.001%

    No Known Activations