© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5552
    Prev
    Next
    INDEX
    Explanations

    cannot and will not fulfill

    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_31_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
     pouvez
    0.65
     можно
    0.64
     lahko
    0.63
     causas
    0.62
     można
    0.61
    ៣
    0.59
     potencialmente
    0.56
     problemlos
    0.56
     sogar
    0.55
     ylab
    0.55
    POSITIVE LOGITS
    퍄
    0.66
    скольку
    0.60
     Nor
    0.59
     längre
    0.59
    实在
    0.57
     emphasises
    0.56
    Behind
    0.56
     apparent
    0.55
    Alliance
    0.55
    보다는
    0.55
    Activations Density 0.128%

    No Known Activations