© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29863
    Prev
    Next
    INDEX
    Explanations

    end of prayers

    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_262k_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
     dif
    0.38
    Dif
    0.36
     divergences
    0.35
    淩
    0.35
    libexec
    0.34
    ອດ
    0.34
     DPR
    0.34
    מת
    0.33
    dys
    0.33
    profitable
    0.33
    POSITIVE LOGITS
     środków
    0.43
     христи
    0.41
     üç
    0.40
     ե
    0.39
     Bewert
    0.39
     nė
    0.39
     मूल्या
    0.38
    ائل
    0.37
     medidas
    0.37
     التربيع
    0.37
    Activations Density 0.002%

    No Known Activations