© 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. 234975
    Prev
    Next
    INDEX
    Explanations

    LGBT organization

    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
    u
    0.54
     global
    0.45
     formidable
    0.43
    ori
    0.42
     Jorg
    0.42
     Pele
    0.41
     GaAs
    0.41
     ,
    0.41
     Marcos
    0.41
     k
    0.40
    POSITIVE LOGITS
    ็ม
    0.54
     আত্মার
    0.50
    Ť
    0.50
    ྥ
    0.50
    ប់
    0.48
     душу
    0.48
     visualise
    0.48
    專輯
    0.48
    ઍ
    0.47
    效
    0.46
    Activations Density 0.000%

    No Known Activations