© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 123
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     ergonomic
    0.52
     ergonom
    0.51
     göra
    0.49
     köpek
    0.48
    <unused77>
    0.48
    ल्ल्या
    0.47
     prêts
    0.47
     découvrir
    0.46
    osphère
    0.46
     odlič
    0.46
    POSITIVE LOGITS
    <blockquote>
    0.59
    In
    0.59
        
    0.56
                
    0.55
    <h4>
    0.55
    0.55
            
    0.54
    <td>
    0.54
    <h3>
    0.53
                                   
    0.52
    Activations Density 0.071%

    No Known Activations