© 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. 52444
    Prev
    Next
    INDEX
    Explanations

    Zakat money

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

    obligatory for adults

    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
     froide
    0.51
    냉
    0.49
     пыта
    0.46
    遵守
    0.46
     ja
    0.46
     мероприятия
    0.45
     बिस्तर
    0.45
     пытается
    0.45
    들은
    0.44
    Описание
    0.44
    POSITIVE LOGITS
    osw
    0.44
    峯
    0.41
    клада
    0.41
     Gonna
    0.41
    𝐠
    0.41
     saudara
    0.40
     ổ
    0.40
     relatif
    0.40
    ناہ
    0.40
    кугӀ
    0.40
    Activations Density 0.000%

    No Known Activations