© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 34
    Prev
    Next
    INDEX
    Explanations

    inserting, assigning, or translating content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    ية
    1.17
    ית
    0.97
     отношение
    0.96
     بالنسبة
    0.96
     berubah
    0.92
    רק
    0.91
    将
    0.90
    theless
    0.87
     estoy
    0.87
     ако
    0.85
    POSITIVE LOGITS
    kannya
    1.10
    ب
    1.05
    된
    1.04
    시켜
    1.03
    Into
    1.01
     into
    0.89
     précie
    0.88
    시킨
    0.87
    রাষ্ট
    0.85
    格納
    0.84
    Activations Density 4.519%

    No Known Activations