© 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. 8919
    Prev
    Next
    INDEX
    Explanations

    reporting or stating facts

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

    The neuron strongly activates on tokens that are proper nouns or named entities (e.g. names of people, places, dates, organizations).

    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
    ;
    0.96
    ”;
    0.89
    ";
    0.89
    ;:
    0.88
    ();
    0.87
    ;}
    0.85
     ;
    0.84
    :";
    0.82
    ";}
    0.80
     "";
    0.78
    POSITIVE LOGITS
     сообщает
    1.33
    reports
    1.11
     reports
    1.09
     berichtet
    1.01
     rapporte
    0.99
     Reports
    0.97
     informó
    0.92
     пишет
    0.90
    Reports
    0.89
     rapporter
    0.89
    Activations Density 0.108%

    No Known Activations