© 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. 7210
    Prev
    Next
    INDEX
    Explanations

    energy kJ/kg systems ISP component

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

    The neuron flags unusually rare or out-of-vocabulary tokens—e.g. proper names, foreign‐language words, or other low-frequency terms.

    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
    𝒆
    0.71
     Celestial
    0.68
    を追加
    0.67
     dyspe
    0.67
    社会主义
    0.65
    ೇ
    0.65
    ถูก
    0.65
     terecht
    0.64
    নমেন্ট
    0.64
     ಮೇಲೆ
    0.64
    POSITIVE LOGITS
    r
    0.96
    s
    0.87
    tac
    0.86
    ר
    0.84
    르
    0.84
    single
    0.81
    ਰ
    0.80
    通信
    0.80
    kgs
    0.80
    té
    0.80
    Activations Density 0.000%

    No Known Activations