© 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. 14015
    Prev
    Next
    INDEX
    Explanations

    This neuron responds most strongly to uncommon or rare words (i.e. tokens with low frequency).

    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
    ግዳ
    0.71
    Три
    0.66
    userService
    0.63
    PostMapping
    0.63
    特效
    0.63
    ገለ
    0.60
    新たな
    0.59
    鋅
    0.59
    枴
    0.59
    智能化
    0.59
    POSITIVE LOGITS
     wasn
    0.92
     didn
    0.92
     isn
    0.92
     ofthe
    0.88
     aren
    0.82
     doesn
    0.79
     before
    0.79
     hadn
    0.79
    '
    0.77
     London
    0.77
    Activations Density 0.046%

    No Known Activations