© 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. 78990
    Prev
    Next
    INDEX
    Explanations

    queen of England

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

    capped upside potential

    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
    apply
    0.52
    your
    0.51
    op
    0.50
    Ana
    0.47
    lt
    0.46
    filepath
    0.46
    FilePath
    0.46
    Ȼ
    0.46
     external
    0.46
    用
    0.46
    POSITIVE LOGITS
     terroir
    0.49
     beauties
    0.49
    愆
    0.48
     बैचलर्स
    0.47
     باع
    0.46
     correctes
    0.46
     spekt
    0.46
     bénéf
    0.45
     katol
    0.45
     phénom
    0.44
    Activations Density 0.001%

    No Known Activations