© 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. 12628
    Prev
    Next
    INDEX
    Explanations

    `f`/`WriteLine`

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting “Read more” (or similar “More” call-to-action) prompts inserted at the ends of content blocks.

    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
    asında
    0.57
    Custodian
    0.57
    
    0.56
    prochen
    0.56
    kses
    0.55
    asının
    0.54
    covariant
    0.54
     забе
    0.54
    ㄞ
    0.53
    )}}{
    0.52
    POSITIVE LOGITS
    Doc
    0.73
     Doc
    0.71
     doc
    0.66
     News
    0.62
    doc
    0.59
     midd
    0.58
     Ball
    0.57
     ජී
    0.57
     Entertainment
    0.56
    Document
    0.55
    Activations Density 0.003%

    No Known Activations