© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    job titles and roles

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

    The neuron strongly activates on personal names and their professional credentials or titles.

    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
    【
    0.57
     cum
    0.50
    ]);
    0.50
    "));
    0.49
     【
    0.46
     semic
    0.46
    겸
    0.46
    之
    0.45
    less
    0.45
    ]));
    0.44
    POSITIVE LOGITS
     Director
    1.27
     Esq
    1.24
     director
    1.23
     directora
    1.17
    Director
    1.13
     CEO
    1.13
    director
    1.11
     président
    1.10
     Curator
    1.10
     president
    1.09
    Activations Density 0.223%

    No Known Activations