© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12799
    Prev
    Next
    INDEX
    Explanations

    mining leases

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

    This neuron picks out vague quantity or amount expressions (e.g. words like “few,” “slew,” “variety,” “such,” etc.).

    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
     bilir
    0.52
    리티
    0.48
    宛
    0.48
     mugs
    0.48
    গি
    0.48
     Metallica
    0.48
    orden
    0.48
     చా
    0.48
    arza
    0.47
     "</
    0.47
    POSITIVE LOGITS
                               
    0.63
                             
    0.57
                              
    0.57
    iscope
    0.57
                           
    0.56
                                 
    0.56
    CLAIM
    0.56
       
    0.55
    𝗨
    0.55
                     
    0.55
    Activations Density 0.011%

    No Known Activations