© 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. 5733
    Prev
    Next
    INDEX
    Explanations

    the current

    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
     aeros
    1.37
     FT
    1.26
     Syl
    1.26
    PCA
    1.24
     봉
    1.23
     lb
    1.18
     ly
    1.18
     ft
    1.17
    poly
    1.17
     PCA
    1.16
    POSITIVE LOGITS
    current
    2.78
     current
    2.69
    Current
    2.57
     CURRENT
    2.49
     Current
    2.43
    CURRENT
    2.35
    currently
    2.29
    当前的
    2.22
    目前的
    2.21
     currently
    2.15
    Activations Density 0.026%

    No Known Activations