© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2983
    Prev
    Next
    INDEX
    Explanations

    in conclusion/summary/essence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     favour
    1.69
    楦
    1.66
    煊
    1.65
     favor
    1.61
    颉
    1.58
    有问题
    1.55
     vacuo
    1.53
     manners
    1.51
     rightful
    1.50
     manner
    1.48
    POSITIVE LOGITS
    그래
    1.69
    oltre
    1.66
    правление
    1.61
     effet
    1.59
    fact
    1.59
    でも
    1.57
    fois
    1.57
     cependant
    1.54
     resumen
    1.53
    ت
    1.52
    Activations Density 0.215%

    No Known Activations