© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8340
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    This neuron detects four-digit numbers representing years (e.g. publication or credit dates) in bibliographic and film/production listings.

    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
     dẫn
    0.58
    ื่น
    0.54
     trailed
    0.53
    례
    0.52
    ));
    0.52
     led
    0.52
    ilg
    0.51
     führt
    0.50
    ;
    0.50
    ulter
    0.49
    POSITIVE LOGITS
    ]()
    1.34
    >()
    1.22
    )()
    1.16
    SuspendLayout
    1.09
    })();
    1.08
    }()
    1.05
    ](../
    1.05
    >();
    1.02
    >().
    1.00
    ](\
    0.99
    Activations Density 0.015%

    No Known Activations