© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15413
    Prev
    Next
    INDEX
    Explanations

    never and always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evangé
    -2.08
    まさか
    -1.83
     relevante
    -1.79
    苙
    -1.70
    個人的には
    -1.69
     coisa
    -1.69
    soit
    -1.67
    îtra
    -1.66
    起码
    -1.66
     ſaid
    -1.65
    POSITIVE LOGITS
    This
    2.20
     when
    2.17
     or
    2.16
    These
    2.16
     These
    1.99
     of
    1.98
     all
    1.94
    这些
    1.90
    这个
    1.88
    8
    1.88
    Activations Density 0.015%

    No Known Activations