© 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. 122520
    Prev
    Next
    INDEX
    Explanations

    Canada, Arar, terrorism links

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

    physical and emotional attraction

    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
    i
    0.55
    ver
    0.45
    ها
    0.44
    滕
    0.44
    ze
    0.43
    um
    0.43
    此之外
    0.40
    \$
    0.39
    ie
    0.38
    ymmetries
    0.38
    POSITIVE LOGITS
     servidores
    0.54
    끙
    0.54
     elevados
    0.53
     २४
    0.52
     maintains
    0.51
     hospitals
    0.51
     bandages
    0.50
     nurseries
    0.50
    তাহাদের
    0.50
     Bình
    0.50
    Activations Density 0.001%

    No Known Activations