© 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. 6421
    Prev
    Next
    INDEX
    Explanations

    workplace contexts or life events

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

    trading decisions

    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
     মুখ্যমন্ত্রী
    0.41
     bahawa
    0.39
     allocated
    0.38
     যাঁরা
    0.38
    市の
    0.38
     തന്നെയാണ്
    0.37
    avaient
    0.37
    <unused56>
    0.36
    ivität
    0.36
     dashed
    0.36
    POSITIVE LOGITS
     религи
    0.38
    ьев
    0.38
    🤸
    0.38
     мира
    0.36
     문제를
    0.36
    Pergunta
    0.36
    가가
    0.36
    ฟ
    0.36
    goers
    0.35
     философии
    0.35
    Activations Density 0.186%

    No Known Activations