© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3239
    Prev
    Next
    INDEX
    Explanations

    or other options

    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
    /
    2.63
    /_
    2.07
    /#
    1.97
    /{
    1.94
    -/
    1.87
     therefore
    1.84
    //
    1.79
    /-/
    1.79
     кожного
    1.78
    /$
    1.78
    POSITIVE LOGITS
     equivalently
    3.53
     else
    3.07
    whatever
    2.98
     zumindest
    2.81
     whatever
    2.77
     nawet
    2.72
     başka
    2.70
     seja
    2.66
     simplemente
    2.63
     siquiera
    2.58
    Activations Density 0.466%

    No Known Activations