© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    fastchat, vicuna, model

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

    This neuron highlights content-bearing tokens—especially technical terms and meaningful nouns, verbs, or adjectives—while largely ignoring common stop words and punctuation.

    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
     troviamo
    1.14
    Фі
    1.12
    実際に
    1.00
    Questa
    0.99
    Під
    0.96
    Ін
    0.95
    優しい
    0.94
    兎
    0.93
     continuidad
    0.92
     کسی
    0.92
    POSITIVE LOGITS
    
    1.72
     yuan
    1.46
     netizens
    1.40
    －
    1.26
     Xiang
    1.25
     jie
    1.20
     zhong
    1.20
     Guangdong
    1.17
     Yuan
    1.16
     Guangzhou
    1.16
    Activations Density 0.831%

    No Known Activations