© 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. 10621
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on unusually rare or low‐frequency tokens (i.e. uncommon 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
    ルイ
    0.82
     rufis
    0.80
     chhoti
    0.80
    る
    0.79
    𝐩
    0.79
    d
    0.79
    𝚜
    0.79
    マ
    0.78
    ラ
    0.77
     ま
    0.77
    POSITIVE LOGITS
     Grafik
    0.88
    away
    0.71
    '>");
    0.71
    ():
    0.71
     düny
    0.69
    encana
    0.69
     Ceylon
    0.68
    ind
    0.68
    graphics
    0.68
    Authenticated
    0.67
    Activations Density 0.000%

    No Known Activations