© 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-262K
    7. 93788
    Prev
    Next
    INDEX
    Explanations

    foreign language and proper nouns

    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
     materiales
    0.46
    閱讀
    0.43
     材料
    0.42
    範圍
    0.41
     مهما
    0.41
     materials
    0.40
     instants
    0.40
    )
    0.40
     può
    0.40
    Material
    0.39
    POSITIVE LOGITS
     Glendale
    0.50
    πή
    0.49
    pte
    0.47
     Давайте
    0.46
     Bakersfield
    0.46
     Dorchester
    0.46
    ပြည်
    0.46
     sute
    0.45
     Angleterre
    0.45
     Lakeside
    0.44
    Activations Density 0.002%

    No Known Activations