© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 468
    Prev
    Next
    INDEX
    Explanations

    preceding a specific word, phrase, or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पत्थर
    2.12
    hanga
    2.10
    நபியே
    2.05
    étape
    2.03
    醣
    2.03
     stately
    1.99
     debuted
    1.98
     フォト
    1.98
    ்க்
    1.95
     Mạnh
    1.93
    POSITIVE LOGITS
    
    1.52
    
    1.44
    یز
    1.41
    𝑢
    1.41
    𝑛
    1.40
    content
    1.33
    
    1.30
     
    1.26
    
    1.26
    
    1.24
    Activations Density 0.000%

    No Known Activations