© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12244
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or tools

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

    The neuron lights up on rare or specialized content‐words (i.e. unusually long or low‐frequency tokens).

    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
     germanium
    0.94
     frightened
    0.91
     PAST
    0.85
     CLT
    0.80
     hag
    0.79
     любых
    0.79
    🧉
    0.77
     Paragu
    0.77
     Jumat
    0.76
     MFG
    0.76
    POSITIVE LOGITS
    లు
    0.81
    分钟
    0.79
    یده
    0.75
    行
    0.73
    ιών
    0.71
    őr
    0.71
     prepara
    0.68
    号
    0.68
    orp
    0.68
    λώ
    0.67
    Activations Density 0.000%

    No Known Activations