© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 202
    Prev
    Next
    INDEX
    Explanations

    wikipedia references

    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_13_width_65k_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
    
    1.37
    
    1.37
    
    1.32
    
    1.31
    
    1.31
     indiscrimin
    1.30
     inadequ
    1.28
    
    1.26
    
    1.24
     inexplicable
    1.23
    POSITIVE LOGITS
    ↵
    1.88
     وذلك
    1.58
    s
    1.51
    ↵↵
    1.49
     Untuk
    1.47
    ség
    1.46
     espaço
    1.46
     ส่ง
    1.42
     глуби
    1.41
     कोत
    1.40
    Activations Density 0.012%

    No Known Activations