© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9134
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on lower-frequency, content-bearing tokens (i.e. non-stopwords) rather than on high-frequency function 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
    рты
    0.98
    тным
    0.93
    trt
    0.92
    캉
    0.84
     venc
    0.84
    뀜
    0.83
    тность
    0.82
     меся
    0.81
    措
    0.81
    ிறது
    0.79
    POSITIVE LOGITS
     perché
    0.77
     グ
    0.77
    لی
    0.72
     avrebbe
    0.68
    را
    0.68
     リビング
    0.68
     Reported
    0.65
     perchè
    0.65
     şi
    0.65
     giornal
    0.64
    Activations Density 0.000%

    No Known Activations