© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13468
    Prev
    Next
    INDEX
    Explanations

    upper extremity, Game Changer, Men's, Cardiac, Orc, Lung, men's bomber, men, Work, Should

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

    The neuron fires on the single key subject noun of each paragraph (e.g. “car,” “Secondary,” “business,” “humerus,” “Rock,” 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_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
     UK
    0.60
    昻
    0.59
     botón
    0.57
     이는
    0.57
     ICRC
    0.57
     USA
    0.56
     Paypal
    0.55
     VMware
    0.54
     zariaden
    0.53
     Salesforce
    0.52
    POSITIVE LOGITS
    或
    0.66
    或者
    0.63
     কিংবা
    0.59
     अथवा
    0.59
     maupun
    0.58
    や
    0.57
     বা
    0.57
    দের
    0.57
     एवं
    0.55
     ಅಥವಾ
    0.55
    Activations Density 0.000%

    No Known Activations