© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6349
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric tokens representing measurements or data values (e.g., percentages, volumes, citation numbers).

    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_31_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
    დ
    0.85
    Estos
    0.84
    ⴹ
    0.70
    dött
    0.70
    İlk
    0.69
    უ
    0.67
    abilità
    0.66
    Efter
    0.66
    ــ
    0.66
    击
    0.66
    POSITIVE LOGITS
     сталки
    0.82
     Merle
    0.79
     ज्वाला
    0.77
     Dickinson
    0.77
    相關文章
    0.76
    obl
    0.75
     Jesus
    0.75
    ocratic
    0.74
     Lafayette
    0.73
     Münster
    0.73
    Activations Density 0.000%

    No Known Activations