© 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. 509
    Prev
    Next
    INDEX
    Explanations

    quantities following "are"

    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
    σμ
    1.66
    thisTrack
    1.66
    رفته
    1.66
    <unused716>
    1.60
     commodo
    1.60
     каким
    1.59
    BSData
    1.58
    <unused1225>
    1.58
    tmpobj
    1.57
     بدی
    1.56
    POSITIVE LOGITS
     eight
    3.26
     seven
    3.22
     nine
    3.21
     six
    3.18
     five
    3.07
     fifteen
    3.02
     fourteen
    3.02
     sixteen
    2.98
     four
    2.96
     seventeen
    2.94
    Activations Density 11.423%

    No Known Activations