© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10286
    Prev
    Next
    INDEX
    Explanations

    sentence initial words or phrases

    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_22_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
    हरु
    1.69
     बच्चो
    1.64
     वो
    1.63
     বেশী
    1.61
    出来る
    1.54
     &
    1.52
    出来ます
    1.48
     কারনে
    1.47
     alot
    1.47
    됬
    1.46
    POSITIVE LOGITS
    
    1.73
    )—
    1.61
    .—
    1.52
    —“
    1.51
    ​—
    1.50
    ϩ
    1.49
    ʿ
    1.45
    ␤
    1.43
    さまざまな
    1.42
    ,—
    1.39
    Activations Density 0.394%

    No Known Activations