© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    the presence of named entities and proper nouns (e.g. topics, places, organizations, and other category labels).

    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
     sogenannten
    0.92
     "":
    0.77
    :</
    0.70
     फिलहाल
    0.70
     '/':
    0.70
     diesem
    0.69
     entsprechenden
    0.69
     আপাতত
    0.69
    この
    0.67
    ちなみに
    0.67
    POSITIVE LOGITS
    、
    2.48
     、
    2.11
    ፣
    2.02
    ၊
    1.97
    ،
    1.94
    !,
    1.91
     、,
    1.88
     тощо
    1.82
    ‌,
    1.80
    ﹑
    1.80
    Activations Density 2.494%

    No Known Activations