© 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. 3514
    Prev
    Next
    INDEX
    Explanations

    football players, positions, and actions

    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
     carelessness
    1.72
    Mathemat
    1.72
     careless
    1.70
    mortem
    1.68
    閣
    1.68
     govern
    1.67
    orders
    1.64
     presidents
    1.64
    genius
    1.64
    govern
    1.63
    POSITIVE LOGITS
     krótk
    1.03
     verkrij
    0.98
    ngl
    0.96
     fibra
    0.92
     télécharg
    0.90
    +][
    0.90
     vorhanden
    0.89
    BSITE
    0.89
    潛
    0.88
     disponibilidad
    0.88
    Activations Density 0.084%

    No Known Activations