© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6853
    Prev
    Next
    INDEX
    Explanations

    what you can do

    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_12_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
     Pursuant
    1.95
    imposed
    1.90
    ?");
    1.81
     Bởi
    1.79
     actes
    1.78
     buscas
    1.76
     Öncelikle
    1.75
     Kindly
    1.74
     ELEMENTS
    1.74
    ?";
    1.74
    POSITIVE LOGITS
     advantage
    1.28
     sock
    1.20
     spare
    1.18
     comfortably
    1.11
     benefit
    1.10
     ahor
    1.09
     comfortable
    1.05
     mak
    1.04
     shortening
    1.03
    不用
    1.03
    Activations Density 0.166%

    No Known Activations