© 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. 129356
    Prev
    Next
    INDEX
    Explanations

    posted or created

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

    stealth fighter, system controls

    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
     WARRANT
    0.44
    들이
    0.43
    譏
    0.42
    釀
    0.41
     काळ
    0.41
     తీవ్ర
    0.40
     الاسم
    0.40
    廣場
    0.40
    ettle
    0.39
    豈
    0.39
    POSITIVE LOGITS
    Energy
    0.49
    Change
    0.48
    goals
    0.48
     lasciato
    0.48
    Chocolate
    0.47
    Goals
    0.47
     volontà
    0.47
    content
    0.46
    Protein
    0.46
    Medicine
    0.46
    Activations Density 0.001%

    No Known Activations