© 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. 238791
    Prev
    Next
    INDEX
    Explanations

    disease knownhis wifediscovered itfor the

    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
    ጲ
    0.48
     correspond
    0.45
    রাষ্ট্রমন্ত্রী
    0.44
    হোক
    0.44
     fabricante
    0.43
    పూర్
    0.43
    бур
    0.43
     лекар
    0.43
    سرائيل
    0.43
    킥
    0.43
    POSITIVE LOGITS
     Signs
    0.50
     الصل
    0.50
     Attention
    0.49
    चणी
    0.49
     Destination
    0.47
     Inference
    0.47
     Promotion
    0.46
    teman
    0.46
    tin
    0.46
     Cina
    0.45
    Activations Density 0.000%

    No Known Activations