© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    end of phrase or list item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     gdyż
    0.66
     takže
    0.56
     protože
    0.54
     \%$.
    0.54
    ായത്
    0.49
    ="))
    0.49
     €.
    0.48
     tomto
    0.48
     ہے۔
    0.47
    ുകളും
    0.47
    POSITIVE LOGITS
    ،
    1.41
    ，
    1.38
    ၊
    1.24
    ,
    1.18
    ፣
    1.07
     ,
    1.04
    ,,
    1.04
    ，《
    1.00
     ،
    1.00
     ，
    0.96
    Activations Density 0.344%

    No Known Activations