© 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. 8679
    Prev
    Next
    INDEX
    Explanations

    breaking down explanations

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

    This neuron detects unusually rare or specialized tokens (e.g. low-frequency technical or proper-noun 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
    ot
    0.97
    i
    0.79
    arity
    0.78
    та
    0.77
     الار
    0.76
     summarizing
    0.74
    呲
    0.74
     laughing
    0.72
    ſt
    0.71
    awai
    0.70
    POSITIVE LOGITS
    で
    0.70
     noct
    0.70
     Hoàng
    0.70
    puede
    0.70
     Noel
    0.69
     MFG
    0.69
    به
    0.68
    larından
    0.68
    াইন
    0.64
     Thủ
    0.64
    Activations Density 0.000%

    No Known Activations