© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8845
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is pick out strongly evaluative or emotionally charged words—tokens that convey a clear stance or feeling.

    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
     Runway
    0.83
     Shall
    0.80
     Blogger
    0.79
     Celebrity
    0.79
     ผม
    0.76
    綬
    0.76
     Nevertheless
    0.76
     Formula
    0.76
    ر
    0.75
     Forth
    0.75
    POSITIVE LOGITS
     обнару
    0.75
    बरोबर
    0.73
     встроен
    0.70
     участок
    0.66
     কাজটি
    0.66
    сный
    0.66
    டம்
    0.65
    த்துடன்
    0.65
    тический
    0.65
     synaptic
    0.64
    Activations Density 0.000%

    No Known Activations