© 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. 137379
    Prev
    Next
    INDEX
    Explanations

    foreign words and Islam

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

    pick a relationship

    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
    卿
    0.53
    ቒ
    0.52
     adaptor
    0.51
    מח
    0.47
     Adaptive
    0.46
     endonuclease
    0.46
    סה
    0.45
     sels
    0.45
    ೦
    0.45
    ಿಕ್
    0.44
    POSITIVE LOGITS
     cualquiera
    0.46
     nhiên
    0.43
     ಯಾವ
    0.42
    ব্যব
    0.41
     Rangers
    0.40
     Crawley
    0.40
     odnosu
    0.40
     xong
    0.39
     houseboat
    0.39
    would
    0.39
    Activations Density 0.001%

    No Known Activations