© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    username must

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

    The neuron fires on prominent list‐item or section‐heading tokens (e.g. the single words or numbers that label subsections or bullet points).

    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
    М
    0.74
     able
    0.73
     transplanted
    0.70
    ות
    0.70
     জ্ঞাত
    0.68
     unable
    0.67
    Ч
    0.65
    t
    0.63
     earlier
    0.61
    В
    0.61
    POSITIVE LOGITS
     âmbito
    0.99
     стаўкі
    0.98
    ᱱ
    0.97
     muest
    0.94
     combinaison
    0.93
     bioquímica
    0.93
     είναι
    0.91
     uniaxial
    0.91
    etera
    0.91
    یل
    0.90
    Activations Density 0.001%

    No Known Activations