© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6409
    Prev
    Next
    INDEX
    Explanations

    too; also

    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
     불구하고
    1.96
    يكون
    1.84
    RECEIVED
    1.82
     wyd
    1.79
    Installed
    1.78
    sentation
    1.75
     Recap
    1.72
     能
    1.71
    了一眼
    1.71
     를
    1.70
    POSITIVE LOGITS
     too
    5.15
    too
    4.03
     TOO
    4.00
     Too
    3.63
    Too
    3.24
     aswell
    2.55
    も
    2.55
     também
    2.48
     тоже
    2.45
     أيضاً
    2.45
    Activations Density 1.106%

    No Known Activations