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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7447
    Prev
    Next
    INDEX
    Explanations

    code comments `#`

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

    The neuron is selectively activating on numeric tokens or literal numbers (including integers and decimals) in text.

    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_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
     Pp
    0.56
     Tabelle
    0.53
     Liste
    0.51
     Questi
    0.51
     typescript
    0.51
     onderdeel
    0.51
     Igual
    0.51
     ∈
    0.51
     pār
    0.51
     från
    0.50
    POSITIVE LOGITS
    ↵↵↵
    0.65
     하지만
    0.63
    ↵↵
    0.59
        
    0.59
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.55
         
    0.54
       
    0.53
    ↵↵↵↵↵↵
    0.53
    陶
    0.52
    奥
    0.51
    Activations Density 0.001%

    No Known Activations