© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3682
    Prev
    Next
    INDEX
    Explanations

    story beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    <h3>
    1.44
    <h2>
    1.28
    </h3>
    1.25
    ↵
    1.23
    </td>
    1.18
    ojana
    1.15
     さん
    1.04
    お子
    1.03
    licka
    1.00
    ↵↵
    0.99
    POSITIVE LOGITS
        
    2.30
                
    2.25
                    
    2.18
                 
    2.16
    ','"+
    2.16
                   
    2.16
    "+"
    2.15
            
    2.12
               
    2.05
           
    2.05
    Activations Density 0.025%

    No Known Activations