© 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. 6885
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on unusually rare or low‐frequency words.

    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
    ці
    0.87
    лу
    0.82
    ъ
    0.80
    ame
    0.80
    வ்வ
    0.78
    ко
    0.76
    č
    0.75
    هم
    0.74
    のス
    0.74
    ห
    0.74
    POSITIVE LOGITS
    olyte
    0.73
     कर्फ
    0.73
     своё
    0.71
     dick
    0.70
     rationality
    0.69
     cuarta
    0.69
     edgecolor
    0.69
     초기
    0.68
    ̈́
    0.68
    汇报
    0.68
    Activations Density 0.000%

    No Known Activations