© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13870
    Prev
    Next
    INDEX
    Explanations

    specific you

    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
    
    1.89
    
    1.53
     quar
    1.43
    ンスター
    1.42
    
    1.41
     voyageurs
    1.39
    	
    1.38
     preliminary
    1.37
     quarrel
    1.37
     aquellas
    1.35
    POSITIVE LOGITS
     TikTok
    2.24
     emoji
    2.18
     adorable
    2.14
     ماما
    2.12
     엄마
    2.08
     ♡
    2.07
     탱
    2.06
     😍
    2.01
     Awesome
    2.01
     Cute
    2.00
    Activations Density 0.469%

    No Known Activations