© 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. 4387
    Prev
    Next
    INDEX
    Explanations

    do that

    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
    aster
    1.21
    +
    0.97
    The
    0.93
     #
    0.89
    zing
    0.87
     The
    0.85
     present
    0.85
    atomy
    0.83
    oting
    0.81
    -
    0.81
    POSITIVE LOGITS
     itu
    4.44
     ấy
    4.11
     ذلك
    4.10
     THAT
    4.01
    THAT
    3.98
     đó
    3.94
     tersebut
    3.77
    That
    3.75
     thats
    3.73
     that
    3.70
    Activations Density 1.962%

    No Known Activations