© 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. 4900
    Prev
    Next
    INDEX
    Explanations

    sun ☀️

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

    The neuron flags stretches of multi‐word service or product names—i.e. long noun phrases describing offerings or technical features.

    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
    መሪያ
    0.61
    ቋ
    0.61
     состава
    0.59
    ەند
    0.57
    铷
    0.57
    ፃ
    0.55
    リリース
    0.55
    ወዳ
    0.55
    ۸
    0.55
    使用
    0.54
    POSITIVE LOGITS
     Raya
    0.75
     '.$
    0.73
     Hampshire
    0.73
     Çünkü
    0.68
     Bournemouth
    0.68
     alpin
    0.67
     lucha
    0.66
     ljubav
    0.66
     aici
    0.64
     ira
    0.64
    Activations Density 0.035%

    No Known Activations