© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50568
    Prev
    Next
    INDEX
    Explanations

    powers not delegated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    אם
    0.48
    א
    0.45
    儲
    0.43
    นะ
    0.43
    駅から
    0.41
    чита
    0.41
     دشمن
    0.40
    כ
    0.40
    ซึ่ง
    0.40
    {(
    0.40
    POSITIVE LOGITS
    ignée
    0.47
     biology
    0.46
     biologie
    0.44
     وطالبات
    0.43
     বাংলাদেশ
    0.41
     صحت
    0.41
     genética
    0.41
     highlight
    0.40
    申请
    0.40
    ürzt
    0.40
    Activations Density 0.004%

    No Known Activations