© 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. 5898
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and formal terms

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

    database services

    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
     horrific
    0.61
     hideous
    0.60
    มะ
    0.53
    ｳ
    0.53
     четырех
    0.53
     abhor
    0.52
    レ
    0.52
    й
    0.51
     terrifying
    0.50
     mystical
    0.50
    POSITIVE LOGITS
     कार्य
    0.53
    comand
    0.52
     Abbreviations
    0.52
     Subsidi
    0.51
    kins
    0.51
     Appendix
    0.48
     evento
    0.48
    Ig
    0.48
    ej
    0.48
    irs
    0.48
    Activations Density 0.000%

    No Known Activations