© 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. 16323
    Prev
    Next
    INDEX
    Explanations

    hope, protection, server

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

    The neuron primarily activates on numeric tokens—especially measurements, decimal values, and other number‐like strings in technical/scientific 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_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
    )、
    0.49
    )。
    0.47
     теркәлүсез
    0.46
     Hotels
    0.46
     Electrons
    0.45
    hence
    0.44
     Denote
    0.44
     乀
    0.43
    bmod
    0.42
     фаразлау
    0.42
    POSITIVE LOGITS
     semangat
    0.58
     badass
    0.58
     debunk
    0.58
    
    0.54
    -...
    0.53
     
    0.53
     davvero
    0.52
     encarg
    0.52
     brazen
    0.52
     artisanal
    0.50
    Activations Density 0.782%

    No Known Activations