© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6113
    Prev
    Next
    INDEX
    Explanations

    comparisons with extreme, greater, less

    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_24_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
     частина
    0.85
    ן
    0.75
     scorsa
    0.72
    区别
    0.71
    צב
    0.71
    ल
    0.71
    Fuente
    0.69
    رة
    0.69
    昨年
    0.69
     Гла
    0.68
    POSITIVE LOGITS
     foliage
    0.88
     lám
    0.86
     inclement
    0.86
     gimbal
    0.84
     streamers
    0.84
     limestone
    0.82
     Omaha
    0.81
     homeostasis
    0.80
     mesothelioma
    0.80
    \|\
    0.79
    Activations Density 0.002%

    No Known Activations