© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65380
    Prev
    Next
    INDEX
    Explanations

    Baha'i and Iranian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鳴
    -0.79
    Grp
    -0.78
     Senators
    -0.78
    IMF
    -0.78
     Sheikh
    -0.74
    Privilege
    -0.73
    lebo
    -0.71
    TRAS
    -0.71
    antra
    -0.68
     islamic
    -0.68
    POSITIVE LOGITS
     Baha
    1.15
     Bah
    1.11
    Baha
    0.99
    Bah
    0.96
     Haifa
    0.92
    ränk
    0.92
     Tablets
    0.91
     baha
    0.87
     Abdu
    0.87
     auxiliar
    0.82
    Activations Density 0.004%

    No Known Activations