© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52713
    Prev
    Next
    INDEX
    Explanations

    words and phrases from letters

    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
     установка
    0.44
    ":(
    0.42
     instalação
    0.40
     {(
    0.40
     Rennen
    0.39
    }(
    0.39
    ρας
    0.38
    )(
    0.38
     সংরক্ষণ
    0.37
    araja
    0.37
    POSITIVE LOGITS
    ्याल
    0.49
    黢
    0.45
     that
    0.45
     maximise
    0.43
     ilə
    0.41
     Maxim
    0.41
    骓
    0.41
    োগ্য
    0.40
    Дата
    0.40
    PARENT
    0.40
    Activations Density 0.002%

    No Known Activations