© 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. 506
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    发现
    0.91
    沣
    0.86
    的行为
    0.84
    怀疑
    0.83
     никаких
    0.83
    有意
    0.80
     reciproc
    0.79
     takiego
    0.79
    分区
    0.79
     real
    0.78
    POSITIVE LOGITS
    aino
    0.60
    /^
    0.60
    ajit
    0.52
    /'
    0.50
    ĩnh
    0.50
    ZO
    0.50
    AMOS
    0.49
    ikon
    0.48
    żej
    0.47
    TES
    0.47
    Activations Density 4.989%

    No Known Activations