© 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. 13840
    Prev
    Next
    INDEX
    Explanations

    Excel, Microsoft, React, secrets, advanced, contradict

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

    The neuron activates on standout technical or domain‐specific tokens—uncommon proper nouns or acronyms (e.g. “microwave,” “Italian,” “ACSs,” “replace”).

    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
    OP
    0.88
     Hold
    0.72
    ss
    0.71
     Space
    0.70
    িত
    0.68
    <0x0D>
    0.65
    mathrm
    0.65
     message
    0.65
     ir
    0.65
     souvenir
    0.63
    POSITIVE LOGITS
    此之外
    1.02
    簑
    0.98
    टीएम
    0.91
    હ
    0.90
    在新
    0.88
    να
    0.82
    蓑
    0.82
    옳
    0.81
    amicin
    0.81
    
    0.81
    Activations Density 0.000%

    No Known Activations