© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14177
    Prev
    Next
    INDEX
    Explanations

    property name="text" type="string"

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized to pick up on hyperlinks—especially the “a href” tag and the “http://” URL strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     इम्मेडिएटली
    0.54
     എന്നീ
    0.53
     आणि
    0.51
     इत्यादी
    0.51
     তাহাদিগের
    0.50
    ೇವಿನ
    0.50
    :**
    0.49
     ইত্যা
    0.49
     등이
    0.49
    érations
    0.48
    POSITIVE LOGITS
               
    0.47
     terza
    0.46
                
    0.44
    instead
    0.44
     trembling
    0.44
                    
    0.43
     stanie
    0.42
    也能
    0.41
     tatt
    0.41
     Tamm
    0.41
    Activations Density 0.002%

    No Known Activations