© 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. 11582
    Prev
    Next
    INDEX
    Explanations

    The neuron detects forum navigation and UI elements such as pagination controls, links (e.g. “Next,” “Load more”), search/profile buttons, page numbers, and post metadata.

    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
     सहयोग
    0.61
    Ана
    0.60
    """.
    0.59
    водство
    0.55
     팔
    0.55
    Sweet
    0.54
    COPY
    0.54
    MODIFY
    0.54
     협
    0.54
    .".
    0.53
    POSITIVE LOGITS
     originally
    0.84
     Originally
    0.79
    originally
    0.77
    Originally
    0.75
     originalmente
    0.70
     coined
    0.59
    بية
    0.56
     initially
    0.54
    τια
    0.53
     ursprünglich
    0.53
    Activations Density 0.019%

    No Known Activations