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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10150
    Prev
    Next
    INDEX
    Explanations

    Westminster, Earth, or Compromise

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

    the presence of numeric figures or measurements (i.e. number tokens, often with decimals).

    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
    er
    0.88
     provoqu
    0.75
     stren
    0.75
     ((
    0.73
    vre
    0.72
    primir
    0.72
    e
    0.70
     auquel
    0.70
    ,
    0.70
     exerted
    0.69
    POSITIVE LOGITS
    Officers
    0.82
    Merchant
    0.82
    Quran
    0.79
    荣誉
    0.77
    Bam
    0.77
    满满
    0.75
    रेडी
    0.75
    前景
    0.75
    Airline
    0.74
    Tourism
    0.74
    Activations Density 0.001%

    No Known Activations