© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    happy birthday

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

    religious texts and biblical figures

    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
    aters
    0.42
     menand
    0.39
    ارة
    0.37
     Nok
    0.37
    祿
    0.37
    originally
    0.37
     highlands
    0.37
    ربية
    0.36
     towns
    0.36
     AIDS
    0.36
    POSITIVE LOGITS
     প্রমুখ
    0.40
    ঘ্রই
    0.39
    循环
    0.39
     나의
    0.39
    🧐
    0.38
    iciencia
    0.38
     મને
    0.37
    Databaze
    0.37
     minimalistic
    0.36
     рам
    0.35
    Activations Density 0.000%

    No Known Activations