© 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. 177232
    Prev
    Next
    INDEX
    Explanations

    performance and efficiency

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

    foreign language and sensitive contexts

    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
     ਉਸ
    0.43
     ഭാഗ
    0.41
     formality
    0.39
     funzionamento
    0.39
     anus
    0.38
     njega
    0.38
    เพิ่มเติม
    0.38
    შ
    0.38
     galima
    0.38
     seman
    0.38
    POSITIVE LOGITS
    Ⲇ
    0.45
     свой
    0.45
     Yard
    0.44
    क्योंकि
    0.44
     Thermodynamic
    0.44
     Lafayette
    0.44
     যেহেতু
    0.44
     университе
    0.44
     Strategy
    0.44
    ेंटिस
    0.43
    Activations Density 0.003%

    No Known Activations