© 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. 228870
    Prev
    Next
    INDEX
    Explanations

    Brazilian asset Jordan Louisiana

    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
     ভেসে
    0.52
     dinyatakan
    0.49
    awesome
    0.48
     শৃ
    0.47
     mengaku
    0.46
    😱
    0.46
     মৃত্য
    0.46
    깎
    0.44
    در
    0.44
     mouve
    0.44
    POSITIVE LOGITS
     Editar
    0.54
     Brazilian
    0.53
     asset
    0.52
     Jordan
    0.51
     Louisiana
    0.51
     Aiden
    0.51
     LGA
    0.50
     Kroger
    0.50
     Asset
    0.49
     SCS
    0.49
    Activations Density 0.001%

    No Known Activations